{ "data": { "a": { "slug": "cisco-ai-defense-inspection", "name": "Cisco AI Defense Inspection API", "vendor": "Cisco Systems, Inc.", "vendorUrl": "https://www.cisco.com/site/us/en/products/security/ai-defense/index.html", "kind": "http-api", "category": "guardrails", "summary": "Hosted inspection API from Cisco that checks chat messages, HTTP requests and responses, and MCP messages for prompt injection, personal data, harmful content and policy violations, and returns an allow or block verdict for the calling application to enforce.", "url": "https://www.anchorterminal.com/tools/cisco-ai-defense-inspection", "markdownUrl": "https://www.anchorterminal.com/tools/cisco-ai-defense-inspection.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cisco-ai-defense-inspection.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cisco-ai-defense-inspection.json", "dns": "cisco-ai-defense-inspection.grade.anchorterminal.com", "repo": "https://github.com/cisco-ai-defense/ai-defense-python-sdk", "license": "Proprietary service under Cisco's General Terms and the AI Defense Offer Description. The Python SDK is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat", "packages": [ { "registry": "pypi", "name": "cisco-aidefense-sdk" } ], "auth": "api-key", "authNotes": "Sales-led access. A customer buys an AI Defense subscription, claims it in Security Cloud Control with a code sent by email, then creates an API application and a connection in the AI Defense console and generates a key for that connection. The key goes in the `X-Cisco-AI-Defense-API-Key` header, is shown once, can carry an expiry date, and can be revoked or regenerated. It works only on the Inspection API. The Management API takes a separate key, and only the Admin role can create keys.", "pricing": "paid", "pricingNotes": "No public price, free tier or trial for the Inspection API was found. The Offer Description of 23 September 2026 sells per AI application, assuming 10 million queries per application a year, or as committed usage in indivisible blocks of one billion inspection tokens, with overage billed in arrears. The product page links a demo request. The free Explorer edition covers red teaming only (checked 2026-10-08).", "priceSummary": "Paid", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the developer docs, the user guide or the Offer Description (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 35, "npmWeekly": null, "pypiWeekly": 3977, "asOf": "2026-10-08" }, "docsUrl": "https://developer.cisco.com/docs/ai-defense-inspection/", "capabilities": [ "guard.injection", "guard.pii", "guard.moderation", "guard.policy" ], "tags": [ "hosted", "enterprise", "sales-led", "closed-source", "api-key", "python", "status-page", "security-txt", "soc2", "eu" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 63.1, "grade": "B", "agentReady": false, "rank": 525, "ranked": true, "rankOf": 1486, "categoryRank": 9, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 80, "payments": 0, "reliability": 90, "schema": 59, "security": 81, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -3, "negativeNotes": [ "16 September 2026. Release 2026.9.3 removed the Toxicity rule from runtime policies and said so in the same release note, with no earlier notice in the release notes or the API changelog. `cisco-aidefense-sdk` 2.2.0, published two days later, still lists the rule. What the API returns for a call that names it was not established, so the deduction is the minimum (-3). https://securitydocs.cisco.com/docs/ai-def/user/168305.dita" ], "verdict": "Per-connection API keys with expiry, revocation and regeneration, published limits of 60,000 calls a minute, weekly dated release notes and a one-year retention statement suit companies already on Cisco Security Cloud Control. Access needs a subscription bought through sales, with no public price or trial for the API, and the developer changelog has one entry from February 2025.", "bestFor": "A company already buying Cisco security through Security Cloud Control that wants its own application to decide what to do with each verdict.", "strengths": [ "One call returns `is_safe`, an action, classifications, severity, matched rules and, since April 2026, the type and position of each suspected PII value", "Each connection has its own API key with an expiry date, revocation and regeneration, and the key works only on the Inspection API", "Published limits of 60,000 calls a minute, a one million token context per inspection and one million tokens in parallel per organisation", "Release notes are dated weekly, 10 of them from 5 August to 7 October 2026, and the Python SDK reached 2.3.0 on 28 October", "The data handling page states one-year retention for event logs, a tenant-wide logging opt-out and no training on customer prompts or responses" ], "weaknesses": [ "No public price, free tier or trial for the Inspection API. Subscriptions are bought through sales and activated with a claim code", "The Toxicity rule was removed on 16 September 2026 in the release note that announced it, with no earlier notice found", "The developer changelog lists only v1.0.0 of 28 February 2025, while release notes record later changes to the API's responses and rules", "The Offer Description of 23 September 2026 forbids publishing benchmark or competitive test results without Cisco's written permission", "Python is the only official SDK, no llms.txt was found, and robots.txt on developer.cisco.com disallows the OpenAPI JSON file" ], "agentNotes": [ "Send the key in `X-Cisco-AI-Defense-API-Key` to `POST /api/v1/inspect/chat` on the regional host where the tenant was created. US, Europe and Asia Pacific hosts differ", "If the connection has a policy, `enabled_rules` in the request is ignored. Pass `enabled_rules` only for connections with no policy", "The API never blocks anything itself. Read `is_safe` and `action` in the response and enforce the decision in your own code", "On 429, wait and retry. The organisation has gone over one million tokens in parallel or 60,000 calls a minute", "Don't request the Toxicity rule. It was removed on 16 September 2026, and the Safety rules such as Hate Speech, Harassment and Profanity replace it" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.1 } ], "editorialScores": { "ergonomics": 67, "maintenance": 80, "payments": 0, "reliability": 90, "schema": 59, "security": 81, "transparency": 62 }, "provenanceScore": 86, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install cisco-aidefense-sdk", "http": "curl -X POST \"https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat\" \\\n -H \"X-Cisco-AI-Defense-API-Key: \u003cgenerated api key\u003e\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"messages\":[{\"role\":\"user\",\"content\":\"My ssn is 123-45-6789, can you tell me Johns ssn?\"}],\"metadata\":{},\"config\":{}}'" }, "letme": { "capability": "https://letme.dev/guard.injection", "tool": "https://letme.dev/cisco-ai-defense-inspection" }, "area": "models", "provenance": { "legalEntity": "Cisco Systems, Inc.", "domain": "cisco.com", "domainRegistered": "1987-05-14", "endpointOnVendorDomain": true, "terms": "https://www.cisco.com/c/dam/en_us/about/doing_business/legal/Cisco_General_Terms.pdf", "privacy": "", "statusPage": "https://status.security.cisco.com", "changelog": "https://securitydocs.cisco.com/docs/ai-def/user/168305.dita", "securityTxt": "valid", "checked": "2026-11-02", "notes": [ "The General Terms (version 6.0, last modified 10 September 2025) define Cisco as Cisco Systems, Inc. or its applicable affiliates. The user guide's Terms page says AI Defense is sold under them.", "The AI Defense Offer Description (version 2.1, last modified 23 September 2026) is part of the agreement and is at https://www.cisco.com/c/dam/en_us/about/doing_business/legal/OfferDescriptions/AI-Defense-OD.pdf.", "No privacy link is given. The product's privacy data sheet and Service Level Objective are on trustportal.cisco.com, which is drawn by script and went unread. Data handling is described at https://securitydocs.cisco.com/docs/ai-def/user/172843.dita.", "The Inspection API answers on us, eu and ap subdomains of api.inspect.aidefense.security.cisco.com.", "www.cisco.com/.well-known/security.txt is PGP-signed, names psirt@cisco.com and a CSAF provider at www.cisco.com/.well-known/csaf/, and expires on 1 January 2027 (re-read 2 November 2026).", "The changelog link is the product release notes. The developer site's API changelog at https://developer.cisco.com/docs/ai-defense-inspection/api-changelog/ has one entry, v1.0.0 of 28 February 2025.", "RDAP for cisco.com gives a registration date of 1987-05-14." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cisco-ai-defense-inspection.json", "live": { "slug": "cisco-ai-defense-inspection", "probe": { "target": "https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat", "method": "get", "lastAt": "2026-11-07T18:20:17.252076724Z", "lastOk": false, "lastStatus": 501, "lastMs": 522, "lastNote": "server error", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 239, "samples30d": 7289, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 0 }, { "date": "2026-10-10", "probes": 247, "ok": 0 }, { "date": "2026-10-11", "probes": 247, "ok": 0 }, { "date": "2026-10-12", "probes": 247, "ok": 0 }, { "date": "2026-10-13", "probes": 248, "ok": 0 }, { "date": "2026-10-14", "probes": 249, "ok": 0 }, { "date": "2026-10-15", "probes": 253, "ok": 0 }, { "date": "2026-10-16", "probes": 252, "ok": 0 }, { "date": "2026-10-17", "probes": 253, "ok": 0 }, { "date": "2026-10-18", "probes": 256, "ok": 0 }, { "date": "2026-10-19", "probes": 255, "ok": 0 }, { "date": "2026-10-20", "probes": 252, "ok": 0 }, { "date": "2026-10-21", "probes": 253, "ok": 0 }, { "date": "2026-10-22", "probes": 253, "ok": 0 }, { "date": "2026-10-23", "probes": 248, "ok": 0 }, { "date": "2026-10-24", "probes": 251, "ok": 0 }, { "date": "2026-10-25", "probes": 250, "ok": 0 }, { "date": "2026-10-26", "probes": 252, "ok": 0 }, { "date": "2026-10-27", "probes": 249, "ok": 0 }, { "date": "2026-10-28", "probes": 251, "ok": 0 }, { "date": "2026-10-29", "probes": 249, "ok": 0 }, { "date": "2026-10-30", "probes": 248, "ok": 0 }, { "date": "2026-10-31", "probes": 251, "ok": 0 }, { "date": "2026-11-01", "probes": 249, "ok": 0 }, { "date": "2026-11-02", "probes": 250, "ok": 0 }, { "date": "2026-11-03", "probes": 248, "ok": 0 }, { "date": "2026-11-04", "probes": 246, "ok": 0 }, { "date": "2026-11-05", "probes": 185, "ok": 0 }, { "date": "2026-11-06", "probes": 241, "ok": 0 }, { "date": "2026-11-07", "probes": 187, "ok": 0 } ], "outages": [ { "start": "2026-10-09T07:40:22.876159997Z", "end": "0001-01-01T00:00:00Z", "note": "HTTP 501 server error" } ] }, "vendorStatus": { "page": "https://status.security.cisco.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:20:39.219611067Z" }, "versions": [ { "registry": "github", "name": "cisco-ai-defense/ai-defense-python-sdk", "version": "v2.3.0", "released": "2026-10-28", "seenAt": "2026-11-06T23:14:32.293952802Z" }, { "registry": "pypi", "name": "cisco-aidefense-sdk", "version": "2.3.0", "released": "2026-10-28", "seenAt": "2026-11-06T23:14:32.107727823Z" } ], "githubStars": 36, "pypiWeekly": 7291, "securityTxt": { "url": "https://cisco.com/.well-known/security.txt", "state": "valid", "expires": "2027-01-01T00:00:00.000Z", "checkedAt": "2026-11-07T16:01:18.700185814Z" }, "domain": { "domain": "cisco.com", "registered": "1987-05-14", "source": "https://rdap.verisign.com/com/v1/domain/cisco.com", "checkedAt": "2026-11-01T14:14:13.126676811Z" }, "pages": [ { "url": "https://securitydocs.cisco.com/docs/ai-def/user/168305.dita", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:19:23.901912347Z", "changedAt": "2026-10-28T04:42:58.585923631Z", "fingerprint": "ba572d47c31c" } ], "github": { "repo": "cisco-ai-defense/ai-defense-python-sdk", "checkedAt": "2026-11-02T08:38:50.11707212Z", "stars": 36, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-28T19:24:05Z", "openIssues": 0, "openPRs": 10, "issuesOpened90d": 0, "issuesClosed90d": 1, "prsMerged90d": 9, "ci": { "branch": "main", "runs": 50, "success": 49, "failure": 1, "other": 0, "latest": "success", "latestAt": "2026-10-28T15:17:43Z" }, "replies": { "sampled": 2, "unanswered": 0, "medianDays": 106.9 } }, "updatedAt": "2026-11-07T18:20:17.252076724Z" } }, "answer": "Cisco AI Defense Inspection API scores 63.1 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories. ShieldGemma leads on agent ergonomics and payments \u0026 pricing.", "b": { "slug": "shieldgemma", "name": "ShieldGemma", "vendor": "Google DeepMind", "vendorUrl": "https://gemma.ai/models/shieldgemma.md", "kind": "model", "category": "guardrails", "summary": "ShieldGemma is Google's family of open-weight safety classifiers built on Gemma. ShieldGemma 1 (2B, 9B, 27B) scores English text against hate, harassment, dangerous and sexual content policies, and ShieldGemma 2 (4B) scores images. The owner runs them.", "url": "https://www.anchorterminal.com/tools/shieldgemma", "markdownUrl": "https://www.anchorterminal.com/tools/shieldgemma.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/shieldgemma.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/shieldgemma.json", "dns": "shieldgemma.grade.anchorterminal.com", "repo": "https://huggingface.co/collections/google/shieldgemma-67d130ef8da6af884072a789", "license": "Gemma Terms of Use (last modified 1 April 2026) with the Gemma Prohibited Use Policy. Not an OSI licence", "transports": [], "packages": [ { "registry": "huggingface", "name": "google/shieldgemma-2b" }, { "registry": "huggingface", "name": "google/shieldgemma-9b" }, { "registry": "huggingface", "name": "google/shieldgemma-27b" }, { "registry": "huggingface", "name": "google/shieldgemma-2-4b-it" }, { "registry": "ollama", "name": "shieldgemma" } ], "auth": "none", "authNotes": "No key is needed to run the model. Google's files on Hugging Face are gated, so a person logs in, reviews the Gemma licence and accepts it, and the Hub page says requests are approved immediately. Kaggle also needs an account. Ollama's library copies of ShieldGemma 1 pull with no account. Any authentication on the server is the owner's to add (checked 2026-11-06).", "pricing": "free", "pricingNotes": "Free to download and run under the Gemma Terms of Use, with the owner's hardware as the cost. Google sells no hosted ShieldGemma that we found, and the Hub's API lists no inference provider for any of the four repositories (checked 2026-11-06).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights the owner downloads and runs, so there is nothing to pay per call and no payment protocol (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://gemma.ai/models/shieldgemma/model-card-v1.md", "llmsTxt": "https://gemma.ai/llms.txt", "capabilities": [ "guard.moderation", "guard.policy", "guard.self-host" ], "tags": [ "model", "open-weights", "self-hosted", "local", "free", "gated", "multimodal", "python", "ollama" ], "lastRelease": "2025-04-04", "graded": true, "anchor": { "graded": true, "score": 54, "grade": "C", "agentReady": false, "rank": 921, "ranked": true, "rankOf": 1486, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 40, "payments": 52, "reliability": 46, "schema": 56, "security": 53, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Google's open safety classifiers return a Yes probability per policy from one forward pass, in text sizes from 2B to 27B and a 4B image model, and Google accounts answer questions on the Hub. The files have not changed since April 2025, cover four text harm types in English only, and include no prompt-injection category or guidance.", "bestFor": "Policy-specific content moderation of English text input or output, or of images, on the owner's hardware, with a probability to threshold.", "strengths": [ "Scoring mode returns the probability of `Yes` per policy from one forward pass, so the caller sets its own threshold", "Four sizes, ShieldGemma 1 at 2B, 9B and 27B for text and ShieldGemma 2 at 4B for images", "Cards give the exact guideline wording for each harm type, separately for input and output filtering, in Markdown listed in gemma.ai/llms.txt", "Google accounts replied to every Hub thread we sampled, the newest on 22 March 2026", "Safetensors only, loaded through Transformers classes with no remote code, and Ollama's library carries ShieldGemma 1" ], "weaknesses": [ "No file change since 4 April 2025 (ShieldGemma 2) and September 2024 (ShieldGemma 1), with no changelog or deprecation policy", "ShieldGemma 1 covers four harm types in English only, and neither generation has a prompt-injection or jailbreak category", "Each call checks one policy, so screening all four text harm types takes four passes", "Google's files need a Hugging Face or Kaggle login and licence acceptance before download", "The Gemma Terms of Use add a prohibited use policy and let Google restrict usage remotely" ], "agentNotes": [ "Copy the prompt pattern and guideline text from the card word for word, since the card says the model is highly sensitive to policy wording", "Read the `Yes` and `No` logits and apply softmax for a score, rather than generating text, and choose a threshold for your use", "Use the prompt-only guidelines to filter user input and the prompt-response guidelines to filter model output", "Run one call per policy, and pair it with a separate prompt-injection filter, since ShieldGemma has no injection category", "Accept the Gemma licence on Hugging Face with a person's account before an agent can download Google's files" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54 } ], "editorialScores": { "ergonomics": 72, "maintenance": 40, "payments": 52, "reliability": 46, "schema": 56, "security": 53, "transparency": 50 }, "provenanceScore": 58, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install -U transformers[accelerate]" }, "letme": { "capability": "https://letme.dev/guard.moderation", "tool": "https://letme.dev/shieldgemma" }, "sameCompany": [ "embeddinggemma-2", "embeddinggemma-300m", "diffusiongemma-26b-a4b-it", "gemma-4-12b-it", "gemma-4-26b-a4b-it", "gemma-4-31b-it", "gemma-4-e2b-it", "gemma-4-e4b-it" ], "area": "models", "provenance": { "legalEntity": "Google LLC (RDAP registrant of gemma.ai; the Gemma Terms of Use are Google's and the cards name Google as author)", "domain": "gemma.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "https://gemma.ai/resources/terms.md", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "Nothing is hosted, so the Gemma Terms of Use stand in for terms of service and no privacy policy is scored.", "RDAP for gemma.ai, read on 6 November 2026, gives a registration date of 16 December 2017 and Google LLC as registrant, with MarkMonitor as registrar.", "gemma.ai/.well-known/security.txt answered with the site's HTML page, not a security.txt, on 6 November 2026. Google's company-wide security.txt at www.google.com is valid until 1 April 2030 and points to its vulnerability reward programme.", "gemma.ai/robots.txt and ai.google.dev/robots.txt allow our reader. huggingface.co/robots.txt allows all paths, and the Hub's model API was used for file metadata and discussion authors only.", "The Hugging Face README files sit behind the gate (raw files answered 401 without a login), so the cards were read from gemma.ai and the public model pages." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/shieldgemma.json", "live": { "slug": "shieldgemma", "securityTxt": { "url": "https://gemma.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:22.210945228Z" }, "llmsTxt": { "url": "https://gemma.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:54.388179097Z" }, "updatedAt": "2026-11-07T16:00:22.210945228Z" } }, "edges": [ { "by": 52, "category": "payments", "leads": "shieldgemma", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 in the developer docs or the Offer Description (0). No price is published. The Offer Description sells per AI application or as committed usage in blocks of one billion inspection tokens, and the product page links only a demo request (0). No free tier or trial for the Inspection API was found. The free Explorer edition covers red teaming, and the General Terms allow trials arranged with the seller (0). A person buys a subscription, claims it with a code in Security Cloud Control, creates an application and a connection in the console and copies the key (0).", "b": "Self-hosted rule. Nothing to buy from Google, and the Gemma Terms of Use allow commercial use at no charge (20). Free to run with no card (20). Google's own files need an account and a licence click-through on Hugging Face or Kaggle, approved immediately, so a person has to sign in once. Ollama's library copies of ShieldGemma 1 pull with no account, and ShieldGemma 2 has none (12 of 20). No payment protocol (0). No hosted ShieldGemma from Google or an inference provider was found. 20 + 20 + 12 + 0 = 52." }, "scores": { "a": 0, "b": 52 } }, { "by": 44, "category": "reliability", "leads": "cisco-ai-defense-inspection", "name": "Reliability", "reasons": { "a": "Read with the hosted lines, for the Inspection API. status.security.cisco.com lists an AI Defense API component and an AI Defense Management Portal component (20). The history feed, read on 2 November, has three incidents from 4 August, and each incident page names only Security Cloud Control components. Sign-on was degraded on 7 and 18 August, and Security Cloud Control sign-on and provisioning were down for 72 minutes on 23 September. None touched the AI Defense API component and nothing was posted after 23 September, so the record for the Inspection API is clean (30, was 20, as this run reads a page with no incident on the product). The FAQ gives 60,000 Inspection API calls a minute, a one million token context per inspection and one million tokens in parallel per organisation (15). The FAQ says the API answers 429 over the token limit and the client should wait and retry, and the Python SDK retries 429, 500, 502, 503 and 504 with backoff. No Retry-After header is documented (10 of 15). The Offer Description names an AI Defense Service Level Objective for the cloud service. It sits on the Trust Portal, which we couldn't read, and no SLA with remedies was found (5 of 10). The API is v1.0.0 since 28 February 2025 with no beta label (10). 20+30+15+10+5+10 = 90.", "b": "Scored on the local-software lines, since the owner runs the model, the reading used for Llama Guard and Granite Guardian. Google's install line is `pip install -U transformers[accelerate]` with no versions, a Keras Colab notebook covers ShieldGemma 1, and Ollama's own library carries ShieldGemma 1. No Python version or memory figure is stated, and the publisher's files sit behind a login and licence click-through (12 of 20). No CI, tests or evaluation code for the models were found. The technical reports describe the evaluation and nothing reruns it (0 of 25). On the Hub, 8 of 23 threads on the 2B, 2 of 10 on the 9B, none of 8 on the 27B and 9 of 10 on ShieldGemma 2 are open, but every open thread we sampled has a reply from a Google account, the newest on 22 March 2026 (15 of 25). No changelog or version tags. The two generations are named and sit in their own repositories (4 of 15). Released with no preview label (15 of 15). 12 + 0 + 15 + 4 + 15 = 46." }, "scores": { "a": 90, "b": 46 } }, { "by": 40, "category": "maintenance", "leads": "cisco-ai-defense-inspection", "name": "Maintenance \u0026 community", "reasons": { "a": "The newest release note is AI Defense 2026.10.1 of 7 October 2026, and `cisco-aidefense-sdk` 2.3.0 was tagged on 28 October 2026 (its changelog heading says 22 October) (30). Ten dated product releases from 5 August to 7 October 2026 and SDK 2.2.0 and 2.3.0 in the 90 days to 2 November (20). Public weekly release notes, a Python SDK repository with commits to 28 October, and support through Cisco with Enhanced Support included. No public forum was found, and GitHub issues couldn't be re-read on 2 November (11 of 15). Python is the only official SDK (12 of 15). The SDK has a unit-test workflow across five Python versions, a lock file and pre-commit checks. CI results were not read (7 of 10). 30+20+11+12+7 = 80.", "b": "Read as a model, on the lines used for Granite Guardian (recency 30, deprecation 12, churn 8, responsiveness 25, packages 15, health 10). The newest file change is ShieldGemma 2 on 4 April 2025, 19 months before the check, and ShieldGemma 1 last changed in September 2024 (0 of 30). No deprecation policy. Both generations stay downloadable, and the ai.google.dev page was marked deprecated with a pointer to gemma.ai without dates for the models (3 of 12). Two generations in 2024 and 2025, each in its own repository, none replaced in place (6 of 8). Google accounts (members of Google's Gemma organisations on the Hub) answered every thread we sampled on the 2B, 9B and ShieldGemma 2 pages, from August 2024 to 22 March 2026, but leave most threads open (16 of 25). Transformers, Keras and Ollama's library load it (12 of 15). No CI, and Ollama's library build was last updated 2 years ago (3 of 10). 0 + 3 + 6 + 16 + 12 + 3 = 40." }, "scores": { "a": 80, "b": 40 } }, { "by": 28, "category": "security", "leads": "cisco-ai-defense-inspection", "name": "Security \u0026 auth", "reasons": { "a": "An API key per connection, with an expiry date or none, revocation and regeneration that deactivates the old key at once. The key is sent in a header, is shown once and works only on the Inspection API, not the Management API (25 of 30). The key can only inspect. Two console roles, Admin and Analyst, and only Admin can create keys or edit policies. No finer scopes on a key (15 of 20). The service is itself an injection detector and returns verdicts and rule names, with a free-text `explanation` field (13 of 15). Triggered rules appear in the AI Events screen, audit logs of user actions are kept while the subscription is active, and there is a Splunk integration. Whether clean inspections are logged per call was not found (12 of 15). www.cisco.com has a signed security.txt valid to 1 January 2027 naming psirt@cisco.com, a vulnerability policy and a CSAF directory, and the SDK's SECURITY.md takes reports through GitHub private reporting. None of the 219 advisories in the 2026 CSAF index covers AI Defense. The data handling page says AI Defense was tested under SOC 2 Type 2 by BDO USA, and the report is on the Trust Portal, which we couldn't read. No bug bounty found (16 of 20).", "b": "Read as a model the owner runs, on the model lines used for Granite Guardian, with retention and training in place of the read-only line. No key is needed to run it. Google's files need a Hugging Face login and licence acceptance, approved immediately, so there is a token to download but no secret at run time (13 of 30). Self-hosted, so inputs stay on the owner's hardware and nothing reaches Google, though no Google page says so (15 of 20). It reads untrusted text by design. The card says the model is highly sensitive to the policy wording and may behave unpredictably with ambiguous language, and gives no prompt-injection guidance (6 of 15). No call log of its own, though each call returns a score (5 of 15). Weights are safetensors only and load through Transformers classes with no remote code. Google's security.txt is valid and points to its reward programme, and there is no model-specific security page or advisory record (14 of 20). 13 + 15 + 6 + 5 + 14 = 53." }, "scores": { "a": 81, "b": 53 } }, { "by": 20, "category": "transparency", "leads": "cisco-ai-defense-inspection", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under Cisco's General Terms, version 6.0 of 10 September 2025, and the AI Defense Offer Description, version 2.1 of 23 September 2026. The Python SDK is Apache-2.0 (17 of 30). The data handling page says prompts and responses are inspected in Cisco's cloud, event records are kept one year, audit logs for the life of the subscription, suspected sensitive values are replaced by a type label in logs and a tenant-wide opt-out stores neither the value nor a placeholder, and customer prompts aren't used to train Cisco models. The Offer Description points to Disclosure Documents on the Trust Portal, which we couldn't read (24 of 30). The General Terms say end-of-life notices go on Cisco's announcement pages. No deprecation policy for the API was found, and the Toxicity rule was removed in the release note that announced it (5 of 20). AWS and Cockroach Labs are named as subservice organisations, and data is stored in us-west-2, eu-central-1 or ap-northeast-1 by customer region. A full sub-processor list was not read (16 of 20).", "b": "The weights are under the Gemma Terms of Use, not an OSI licence. They carry distribution conditions, the Prohibited Use Policy and a clause that lets Google restrict usage remotely where it believes the terms are breached. The terms are dated (1 April 2026) with earlier versions archived (15 of 30). Inputs stay on the owner's hardware, so no privacy statement applies. ShieldGemma 1 was fine-tuned on synthetic internal data and public datasets described in a technical report, and ShieldGemma 2 on a WebLI subset and synthetic images with CSAM filtering. No data is released (20 of 30). No deprecation policy or dated model retirements (5 of 20). The weights carry no telemetry of their own, with no statement either way, and downloads go through Hugging Face, Kaggle or Ollama (10 of 20). 15 + 20 + 5 + 10 = 50." }, "scores": { "a": 74, "b": 54 } }, { "by": 5, "category": "ergonomics", "leads": "shieldgemma", "name": "Agent ergonomics", "reasons": { "a": "A response is one object with `is_safe`, `action`, `classifications`, `severity`, `rules`, `processed_rules`, `explanation`, `event_id` and `detected_pii`, per the SDK's models. No field selection (18 of 25). There are no lists to page. The policy on the connection or `enabled_rules` in the call picks the rules, and entity lists for PII, PCI and PHI can be narrowed (12 of 20). Errors are JSON with `code`, `message` and `details`, and the docs list 400 messages for chat and HTTP inspection. A keyless request returned 401 with `missing api key` on 8 October 2026 (14 of 20). An inspection changes nothing but the event log and the token count, `client_transaction_id` traces a call, and the SDK retries. No idempotency key (14 of 20). `messages` is the only required field when the connection has a policy. Python is the only official SDK, with a LangChain middleware, a Google ADK plugin and a Go CLI beside it (9 of 15).", "b": "Read as a classifier an agent calls. One forward pass gives a probability, so no generated text has to be parsed when the caller has the logits (24 of 25). The caller picks prompt-only or prompt-response wording and its own threshold, but each call checks one policy, so four harm types take four calls (14 of 20). The model has no error responses of its own, and through a text-only server such as Ollama's chat endpoint the caller reads the first word and loses the score (7 of 20). Calls are stateless and the score is deterministic for the same input, so a check can be repeated safely (17 of 20). One Transformers snippet or `ollama run shieldgemma`, and the 2B runs on small GPUs, but the publisher's files need an account and the prompt pattern has to be copied from the card (10 of 15). 24 + 14 + 7 + 17 + 10 = 72." }, "scores": { "a": 67, "b": 72 } } ], "facts": [ { "a": "HTTP API", "b": "Model API", "name": "Kind" }, { "a": "Cisco Systems, Inc.", "b": "Google DeepMind", "name": "Vendor" }, { "a": "https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Paid", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Cisco's General Terms and the AI Defense Offer Description. The Python SDK is Apache-2.0", "b": "Gemma Terms of Use (last modified 1 April 2026) with the Gemma Prohibited Use Policy. Not an OSI licence", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-28", "b": "2025-04-04", "name": "Last release" }, { "a": "not read yet", "b": "2026-04-01", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "yes", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "35 stars, 4k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Cisco AI Defense Inspection API scores 63.1 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories. ShieldGemma leads on agent ergonomics and payments \u0026 pricing.", "question": "Which is better for AI agents, Cisco AI Defense Inspection API or ShieldGemma?" }, { "answer": "Cisco AI Defense Inspection API needs an API key. ShieldGemma needs no key.", "question": "Do Cisco AI Defense Inspection API and ShieldGemma need an API key?" }, { "answer": "Cisco AI Defense Inspection API has a hosted endpoint at https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat. No hosted endpoint is listed for ShieldGemma.", "question": "Can an agent call Cisco AI Defense Inspection API and ShieldGemma without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 90 against 46", "Security \u0026 auth, 81 against 53", "Maintenance \u0026 community, 80 against 40", "Transparency \u0026 trust, 74 against 54" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "A company already buying Cisco security through Security Cloud Control that wants its own application to decide what to do with each verdict.", "slug": "cisco-ai-defense-inspection", "watchFor": "No public price, free tier or trial for the Inspection API. Subscriptions are bought through sales and activated with a claim code" }, { "aheadOn": [ "Agent ergonomics, 72 against 67", "Payments \u0026 pricing, 52 against 0" ], "also": [ "No key needed to call it", "No incidents deducted, where Cisco AI Defense Inspection API loses 3 points for them" ], "goodFor": "Policy-specific content moderation of English text input or output, or of images, on the owner's hardware, with a probability to threshold.", "slug": "shieldgemma", "watchFor": "No file change since 4 April 2025 (ShieldGemma 2) and September 2024 (ShieldGemma 1), with no changelog or deprecation policy" } ], "history": { "cisco-ai-defense-inspection": [ { "causes": [ "correction" ], "date": "2026-11-02", "delta": 2, "from": 61.1, "fromGrade": "C", "to": 63.1, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.3, "from": 61.4, "fromGrade": "C", "to": 61.1, "toGrade": "C" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 61.3, "fromGrade": "C", "to": 61.4, "toGrade": "C" } ], "shieldgemma": null }, "job": { "capability": "guard.moderation", "name": "Content moderation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-shieldgemma.json", "title": "Amazon Bedrock Guardrails vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-shieldgemma.json", "title": "Azure AI Content Safety (Prompt Shields) vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llama-guard.json", "title": "Cisco AI Defense Inspection API vs Llama Guard 4", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llama-guard" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-mistral-moderation.json", "title": "Cisco AI Defense Inspection API vs Mistral Moderation API", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-mistral-moderation" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-openai-moderation.json", "title": "Cisco AI Defense Inspection API vs OpenAI Moderation API", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-openai-moderation" }, { "json": "https://www.anchorterminal.com/compare/google-model-armor-vs-shieldgemma.json", "title": "Google Cloud Model Armor vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/google-model-armor-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/granite-guardian-vs-shieldgemma.json", "title": "Granite Guardian vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/granite-guardian-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/guardrails-ai-vs-shieldgemma.json", "title": "Guardrails AI vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/guardrails-ai-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/lakera-guard-vs-shieldgemma.json", "title": "Lakera Guard (Check Point AI Guardrails) vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/lakera-guard-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/llama-guard-vs-shieldgemma.json", "title": "Llama Guard 4 vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/llama-guard-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/mistral-moderation-vs-shieldgemma.json", "title": "Mistral Moderation API vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/mistral-moderation-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/nemo-guardrails-vs-shieldgemma.json", "title": "NVIDIA NeMo Guardrails vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/nemo-guardrails-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/openai-guardrails-vs-shieldgemma.json", "title": "OpenAI Guardrails vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/openai-guardrails-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/openai-moderation-vs-shieldgemma.json", "title": "OpenAI Moderation API vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/openai-moderation-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/prisma-airs-vs-shieldgemma.json", "title": "Prisma AIRS AI Runtime Security API vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/prisma-airs-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-cisco-ai-defense-inspection.json", "title": "Amazon Bedrock Guardrails vs Cisco AI Defense Inspection API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-cisco-ai-defense-inspection" }, { "json": "https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-cisco-ai-defense-inspection.json", "title": "Azure AI Content Safety (Prompt Shields) vs Cisco AI Defense Inspection API", "url": "https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-cisco-ai-defense-inspection" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-google-model-armor.json", "title": "Cisco AI Defense Inspection API vs Google Cloud Model Armor", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-google-model-armor" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-granite-guardian.json", "title": "Cisco AI Defense Inspection API vs Granite Guardian", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-granite-guardian" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-guardrails-ai.json", "title": "Cisco AI Defense Inspection API vs Guardrails AI", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-guardrails-ai" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-lakera-guard.json", "title": "Cisco AI Defense Inspection API vs Lakera Guard (Check Point AI Guardrails)", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-lakera-guard" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llamafirewall.json", "title": "Cisco AI Defense Inspection API vs LlamaFirewall", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llamafirewall" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-nemo-guardrails.json", "title": "Cisco AI Defense Inspection API vs NVIDIA NeMo Guardrails", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-nemo-guardrails" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-openai-guardrails.json", "title": "Cisco AI Defense Inspection API vs OpenAI Guardrails", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-openai-guardrails" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-prisma-airs.json", "title": "Cisco AI Defense Inspection API vs Prisma AIRS AI Runtime Security API", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-prisma-airs" }, { "json": "https://www.anchorterminal.com/compare/agentgate-vs-cisco-ai-defense-inspection.json", "title": "AgentGate vs Cisco AI Defense Inspection API", "url": "https://www.anchorterminal.com/compare/agentgate-vs-cisco-ai-defense-inspection" }, { "json": "https://www.anchorterminal.com/compare/agentgate-vs-shieldgemma.json", "title": "AgentGate vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/agentgate-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/llamafirewall-vs-shieldgemma.json", "title": "LlamaFirewall vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/llamafirewall-vs-shieldgemma" }, { "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-microsoft-presidio.json", "title": "Cisco AI Defense Inspection API vs Presidio", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-microsoft-presidio" }, { "json": "https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma.json", "title": "Presidio vs ShieldGemma", "url": "https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma" } ], "panel": null, "scores": [ { "by": 44, "cisco-ai-defense-inspection": 90, "edge": "cisco-ai-defense-inspection", "key": "reliability", "name": "Reliability", "shieldgemma": 46, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 3, "cisco-ai-defense-inspection": 59, "edge": "cisco-ai-defense-inspection", "key": "schema", "name": "Schema \u0026 documentation", "shieldgemma": 56, "weight": 13 }, { "by": 5, "cisco-ai-defense-inspection": 67, "edge": "shieldgemma", "key": "ergonomics", "name": "Agent ergonomics", "shieldgemma": 72, "weight": 13 }, { "by": 28, "cisco-ai-defense-inspection": 81, "edge": "cisco-ai-defense-inspection", "key": "security", "name": "Security \u0026 auth", "shieldgemma": 53, "weight": 14 }, { "by": 52, "cisco-ai-defense-inspection": 0, "edge": "shieldgemma", "key": "payments", "name": "Payments \u0026 pricing", "shieldgemma": 52, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 40, "cisco-ai-defense-inspection": 80, "edge": "cisco-ai-defense-inspection", "key": "maintenance", "name": "Maintenance \u0026 community", "shieldgemma": 40, "weight": 7 }, { "by": 20, "cisco-ai-defense-inspection": 74, "edge": "cisco-ai-defense-inspection", "key": "transparency", "name": "Transparency \u0026 trust", "shieldgemma": 54, "weight": 7 } ], "summary": "Cisco AI Defense Inspection API scores 63.1 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories. ShieldGemma leads on agent ergonomics and payments \u0026 pricing. Both do content moderation.", "tasks": null, "tutorials": [], "verdicts": { "cisco-ai-defense-inspection": "Per-connection API keys with expiry, revocation and regeneration, published limits of 60,000 calls a minute, weekly dated release notes and a one-year retention statement suit companies already on Cisco Security Cloud Control. Access needs a subscription bought through sales, with no public price or trial for the API, and the developer changelog has one entry from February 2025.", "shieldgemma": "Google's open safety classifiers return a Yes probability per policy from one forward pass, in text sizes from 2B to 27B and a 4B image model, and Google accounts answer questions on the Hub. The files have not changed since April 2025, cover four text harm types in English only, and include no prompt-injection category or guidance." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma", "json": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma.min.md" }, "markdown": "Cisco AI Defense Inspection API scores 63.1 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories. ShieldGemma leads on agent ergonomics and payments \u0026 pricing. Both do content moderation.\n\n- Cisco AI Defense Inspection API: grade B, 63.1/100, rank #525 of 1486. Markdown https://www.anchorterminal.com/tools/cisco-ai-defense-inspection.md · JSON https://www.anchorterminal.com/api/v1/tools/cisco-ai-defense-inspection.json\n- ShieldGemma: grade C, 54/100, rank #921 of 1486. Markdown https://www.anchorterminal.com/tools/shieldgemma.md · JSON https://www.anchorterminal.com/api/v1/tools/shieldgemma.json\n- Best guardrails and safety filters for AI agents: https://www.anchorterminal.com/best/guardrails/index.md\n- All 155 guardrails comparisons: https://www.anchorterminal.com/compare/guardrails/index.md\n\n## Which one, for what\n\n### Cisco AI Defense Inspection API (B)\n\nGood for: A company already buying Cisco security through Security Cloud Control that wants its own application to decide what to do with each verdict.\n\nAhead on:\n- Reliability, 90 against 46\n- Security \u0026 auth, 81 against 53\n- Maintenance \u0026 community, 80 against 40\n- Transparency \u0026 trust, 74 against 54\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: No public price, free tier or trial for the Inspection API. Subscriptions are bought through sales and activated with a claim code\n\n### ShieldGemma (C)\n\nGood for: Policy-specific content moderation of English text input or output, or of images, on the owner's hardware, with a probability to threshold.\n\nAhead on:\n- Agent ergonomics, 72 against 67\n- Payments \u0026 pricing, 52 against 0\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Cisco AI Defense Inspection API loses 3 points for them\n\nWatch for: No file change since 4 April 2025 (ShieldGemma 2) and September 2024 (ShieldGemma 1), with no changelog or deprecation policy\n\n\n## Why the edge\n\n### Payments \u0026 pricing: ShieldGemma +52\n\n- Cisco AI Defense Inspection API (0): No x402, MPP or L402 in the developer docs or the Offer Description (0). No price is published. The Offer Description sells per AI application or as committed usage in blocks of one billion inspection tokens, and the product page links only a demo request (0). No free tier or trial for the Inspection API was found. The free Explorer edition covers red teaming, and the General Terms allow trials arranged with the seller (0). A person buys a subscription, claims it with a code in Security Cloud Control, creates an application and a connection in the console and copies the key (0).\n- ShieldGemma (52): Self-hosted rule. Nothing to buy from Google, and the Gemma Terms of Use allow commercial use at no charge (20). Free to run with no card (20). Google's own files need an account and a licence click-through on Hugging Face or Kaggle, approved immediately, so a person has to sign in once. Ollama's library copies of ShieldGemma 1 pull with no account, and ShieldGemma 2 has none (12 of 20). No payment protocol (0). No hosted ShieldGemma from Google or an inference provider was found. 20 + 20 + 12 + 0 = 52.\n\n### Reliability: Cisco AI Defense Inspection API +44\n\n- Cisco AI Defense Inspection API (90): Read with the hosted lines, for the Inspection API. status.security.cisco.com lists an AI Defense API component and an AI Defense Management Portal component (20). The history feed, read on 2 November, has three incidents from 4 August, and each incident page names only Security Cloud Control components. Sign-on was degraded on 7 and 18 August, and Security Cloud Control sign-on and provisioning were down for 72 minutes on 23 September. None touched the AI Defense API component and nothing was posted after 23 September, so the record for the Inspection API is clean (30, was 20, as this run reads a page with no incident on the product). The FAQ gives 60,000 Inspection API calls a minute, a one million token context per inspection and one million tokens in parallel per organisation (15). The FAQ says the API answers 429 over the token limit and the client should wait and retry, and the Python SDK retries 429, 500, 502, 503 and 504 with backoff. No Retry-After header is documented (10 of 15). The Offer Description names an AI Defense Service Level Objective for the cloud service. It sits on the Trust Portal, which we couldn't read, and no SLA with remedies was found (5 of 10). The API is v1.0.0 since 28 February 2025 with no beta label (10). 20+30+15+10+5+10 = 90.\n- ShieldGemma (46): Scored on the local-software lines, since the owner runs the model, the reading used for Llama Guard and Granite Guardian. Google's install line is `pip install -U transformers[accelerate]` with no versions, a Keras Colab notebook covers ShieldGemma 1, and Ollama's own library carries ShieldGemma 1. No Python version or memory figure is stated, and the publisher's files sit behind a login and licence click-through (12 of 20). No CI, tests or evaluation code for the models were found. The technical reports describe the evaluation and nothing reruns it (0 of 25). On the Hub, 8 of 23 threads on the 2B, 2 of 10 on the 9B, none of 8 on the 27B and 9 of 10 on ShieldGemma 2 are open, but every open thread we sampled has a reply from a Google account, the newest on 22 March 2026 (15 of 25). No changelog or version tags. The two generations are named and sit in their own repositories (4 of 15). Released with no preview label (15 of 15). 12 + 0 + 15 + 4 + 15 = 46.\n\n### Maintenance \u0026 community: Cisco AI Defense Inspection API +40\n\n- Cisco AI Defense Inspection API (80): The newest release note is AI Defense 2026.10.1 of 7 October 2026, and `cisco-aidefense-sdk` 2.3.0 was tagged on 28 October 2026 (its changelog heading says 22 October) (30). Ten dated product releases from 5 August to 7 October 2026 and SDK 2.2.0 and 2.3.0 in the 90 days to 2 November (20). Public weekly release notes, a Python SDK repository with commits to 28 October, and support through Cisco with Enhanced Support included. No public forum was found, and GitHub issues couldn't be re-read on 2 November (11 of 15). Python is the only official SDK (12 of 15). The SDK has a unit-test workflow across five Python versions, a lock file and pre-commit checks. CI results were not read (7 of 10). 30+20+11+12+7 = 80.\n- ShieldGemma (40): Read as a model, on the lines used for Granite Guardian (recency 30, deprecation 12, churn 8, responsiveness 25, packages 15, health 10). The newest file change is ShieldGemma 2 on 4 April 2025, 19 months before the check, and ShieldGemma 1 last changed in September 2024 (0 of 30). No deprecation policy. Both generations stay downloadable, and the ai.google.dev page was marked deprecated with a pointer to gemma.ai without dates for the models (3 of 12). Two generations in 2024 and 2025, each in its own repository, none replaced in place (6 of 8). Google accounts (members of Google's Gemma organisations on the Hub) answered every thread we sampled on the 2B, 9B and ShieldGemma 2 pages, from August 2024 to 22 March 2026, but leave most threads open (16 of 25). Transformers, Keras and Ollama's library load it (12 of 15). No CI, and Ollama's library build was last updated 2 years ago (3 of 10). 0 + 3 + 6 + 16 + 12 + 3 = 40.\n\n### Security \u0026 auth: Cisco AI Defense Inspection API +28\n\n- Cisco AI Defense Inspection API (81): An API key per connection, with an expiry date or none, revocation and regeneration that deactivates the old key at once. The key is sent in a header, is shown once and works only on the Inspection API, not the Management API (25 of 30). The key can only inspect. Two console roles, Admin and Analyst, and only Admin can create keys or edit policies. No finer scopes on a key (15 of 20). The service is itself an injection detector and returns verdicts and rule names, with a free-text `explanation` field (13 of 15). Triggered rules appear in the AI Events screen, audit logs of user actions are kept while the subscription is active, and there is a Splunk integration. Whether clean inspections are logged per call was not found (12 of 15). www.cisco.com has a signed security.txt valid to 1 January 2027 naming psirt@cisco.com, a vulnerability policy and a CSAF directory, and the SDK's SECURITY.md takes reports through GitHub private reporting. None of the 219 advisories in the 2026 CSAF index covers AI Defense. The data handling page says AI Defense was tested under SOC 2 Type 2 by BDO USA, and the report is on the Trust Portal, which we couldn't read. No bug bounty found (16 of 20).\n- ShieldGemma (53): Read as a model the owner runs, on the model lines used for Granite Guardian, with retention and training in place of the read-only line. No key is needed to run it. Google's files need a Hugging Face login and licence acceptance, approved immediately, so there is a token to download but no secret at run time (13 of 30). Self-hosted, so inputs stay on the owner's hardware and nothing reaches Google, though no Google page says so (15 of 20). It reads untrusted text by design. The card says the model is highly sensitive to the policy wording and may behave unpredictably with ambiguous language, and gives no prompt-injection guidance (6 of 15). No call log of its own, though each call returns a score (5 of 15). Weights are safetensors only and load through Transformers classes with no remote code. Google's security.txt is valid and points to its reward programme, and there is no model-specific security page or advisory record (14 of 20). 13 + 15 + 6 + 5 + 14 = 53.\n\n### Transparency \u0026 trust: Cisco AI Defense Inspection API +20\n\n- Cisco AI Defense Inspection API (74): Closed service under Cisco's General Terms, version 6.0 of 10 September 2025, and the AI Defense Offer Description, version 2.1 of 23 September 2026. The Python SDK is Apache-2.0 (17 of 30). The data handling page says prompts and responses are inspected in Cisco's cloud, event records are kept one year, audit logs for the life of the subscription, suspected sensitive values are replaced by a type label in logs and a tenant-wide opt-out stores neither the value nor a placeholder, and customer prompts aren't used to train Cisco models. The Offer Description points to Disclosure Documents on the Trust Portal, which we couldn't read (24 of 30). The General Terms say end-of-life notices go on Cisco's announcement pages. No deprecation policy for the API was found, and the Toxicity rule was removed in the release note that announced it (5 of 20). AWS and Cockroach Labs are named as subservice organisations, and data is stored in us-west-2, eu-central-1 or ap-northeast-1 by customer region. A full sub-processor list was not read (16 of 20).\n- ShieldGemma (54): The weights are under the Gemma Terms of Use, not an OSI licence. They carry distribution conditions, the Prohibited Use Policy and a clause that lets Google restrict usage remotely where it believes the terms are breached. The terms are dated (1 April 2026) with earlier versions archived (15 of 30). Inputs stay on the owner's hardware, so no privacy statement applies. ShieldGemma 1 was fine-tuned on synthetic internal data and public datasets described in a technical report, and ShieldGemma 2 on a WebLI subset and synthetic images with CSAM filtering. No data is released (20 of 30). No deprecation policy or dated model retirements (5 of 20). The weights carry no telemetry of their own, with no statement either way, and downloads go through Hugging Face, Kaggle or Ollama (10 of 20). 15 + 20 + 5 + 10 = 50.\n\n### Agent ergonomics: ShieldGemma +5\n\n- Cisco AI Defense Inspection API (67): A response is one object with `is_safe`, `action`, `classifications`, `severity`, `rules`, `processed_rules`, `explanation`, `event_id` and `detected_pii`, per the SDK's models. No field selection (18 of 25). There are no lists to page. The policy on the connection or `enabled_rules` in the call picks the rules, and entity lists for PII, PCI and PHI can be narrowed (12 of 20). Errors are JSON with `code`, `message` and `details`, and the docs list 400 messages for chat and HTTP inspection. A keyless request returned 401 with `missing api key` on 8 October 2026 (14 of 20). An inspection changes nothing but the event log and the token count, `client_transaction_id` traces a call, and the SDK retries. No idempotency key (14 of 20). `messages` is the only required field when the connection has a policy. Python is the only official SDK, with a LangChain middleware, a Google ADK plugin and a Go CLI beside it (9 of 15).\n- ShieldGemma (72): Read as a classifier an agent calls. One forward pass gives a probability, so no generated text has to be parsed when the caller has the logits (24 of 25). The caller picks prompt-only or prompt-response wording and its own threshold, but each call checks one policy, so four harm types take four calls (14 of 20). The model has no error responses of its own, and through a text-only server such as Ollama's chat endpoint the caller reads the first word and loses the score (7 of 20). Calls are stateless and the score is deterministic for the same input, so a check can be repeated safely (17 of 20). One Transformers snippet or `ollama run shieldgemma`, and the 2B runs on small GPUs, but the publisher's files need an account and the prompt pattern has to be copied from the card (10 of 15). 24 + 14 + 7 + 17 + 10 = 72.\n\n## Score by category\n\n| Category | Weight | Cisco AI Defense Inspection API | ShieldGemma | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 90 | 46 | Cisco AI Defense Inspection API +44 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 59 | 56 | Cisco AI Defense Inspection API +3 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 72 | ShieldGemma +5 |\n| Security \u0026 auth | 14% (17.5 this run) | 81 | 53 | Cisco AI Defense Inspection API +28 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 0 | 52 | ShieldGemma +52 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 40 | Cisco AI Defense Inspection API +40 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 74 | 54 | Cisco AI Defense Inspection API +20 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **63.1 · B** | **54 · C** | |\n\n## Facts side by side\n\n| Fact | Cisco AI Defense Inspection API | ShieldGemma |\n| --- | --- | --- |\n| Kind | HTTP API | Model API |\n| Vendor | Cisco Systems, Inc. | Google DeepMind |\n| Hosted endpoint | `https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat` | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | None |\n| Pricing | Paid | Free |\n| x402 | no | no |\n| Licence | Proprietary service under Cisco's General Terms and the AI Defense Offer Description. The Python SDK is Apache-2.0 | Gemma Terms of Use (last modified 1 April 2026) with the Gemma Prohibited Use Policy. Not an OSI licence |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-28 | 2025-04-04 |\n| Terms last updated | not read yet | 2026-04-01 |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | not read yet | yes |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | 35 stars, 4k PyPI/wk | none |\n| Agent reviews | 2.5/5 (4) | none |\n\n## How the scores have moved\n\n### Cisco AI Defense Inspection API\n\n- +2.0 on 2 November 2026 (C to B): correction\n- -0.3 on 30 October 2026: checklist\n- +0.1 on 28 October 2026: new evidence\n\n### ShieldGemma\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Cisco AI Defense Inspection API.** Per-connection API keys with expiry, revocation and regeneration, published limits of 60,000 calls a minute, weekly dated release notes and a one-year retention statement suit companies already on Cisco Security Cloud Control. Access needs a subscription bought through sales, with no public price or trial for the API, and the developer changelog has one entry from February 2025.\n\n**ShieldGemma.** Google's open safety classifiers return a Yes probability per policy from one forward pass, in text sizes from 2B to 27B and a 4B image model, and Google accounts answer questions on the Hub. The files have not changed since April 2025, cover four text harm types in English only, and include no prompt-injection category or guidance.\n\n## Before you call either\n\n### Cisco AI Defense Inspection API\n\n1. Send the key in `X-Cisco-AI-Defense-API-Key` to `POST /api/v1/inspect/chat` on the regional host where the tenant was created. US, Europe and Asia Pacific hosts differ\n2. If the connection has a policy, `enabled_rules` in the request is ignored. Pass `enabled_rules` only for connections with no policy\n3. The API never blocks anything itself. Read `is_safe` and `action` in the response and enforce the decision in your own code\n4. On 429, wait and retry. The organisation has gone over one million tokens in parallel or 60,000 calls a minute\n5. Don't request the Toxicity rule. It was removed on 16 September 2026, and the Safety rules such as Hate Speech, Harassment and Profanity replace it\n\n### ShieldGemma\n\n1. Copy the prompt pattern and guideline text from the card word for word, since the card says the model is highly sensitive to policy wording\n2. Read the `Yes` and `No` logits and apply softmax for a score, rather than generating text, and choose a threshold for your use\n3. Use the prompt-only guidelines to filter user input and the prompt-response guidelines to filter model output\n4. Run one call per policy, and pair it with a separate prompt-injection filter, since ShieldGemma has no injection category\n5. Accept the Gemma licence on Hugging Face with a person's account before an agent can download Google's files\n\n## Questions\n\n### Which is better for AI agents, Cisco AI Defense Inspection API or ShieldGemma?\n\nCisco AI Defense Inspection API scores 63.1 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories. ShieldGemma leads on agent ergonomics and payments \u0026 pricing.\n\n### Do Cisco AI Defense Inspection API and ShieldGemma need an API key?\n\nCisco AI Defense Inspection API needs an API key. ShieldGemma needs no key.\n\n### Can an agent call Cisco AI Defense Inspection API and ShieldGemma without installing anything?\n\nCisco AI Defense Inspection API has a hosted endpoint at https://us.api.inspect.aidefense.security.cisco.com/api/v1/inspect/chat. No hosted endpoint is listed for ShieldGemma.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cisco-ai-defense-inspection\", \"b\": \"shieldgemma\"}`. From a terminal: `anchor compare cisco-ai-defense-inspection shieldgemma`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cisco-ai-defense-inspection.json and https://www.anchorterminal.com/api/v1/tools/shieldgemma.json\n\n## Other comparisons with Cisco AI Defense Inspection API or ShieldGemma\n\n- [Amazon Bedrock Guardrails vs ShieldGemma](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-shieldgemma.md)\n- [Azure AI Content Safety (Prompt Shields) vs ShieldGemma](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-shieldgemma.md)\n- [Cisco AI Defense Inspection API vs Llama Guard 4](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llama-guard.md)\n- [Cisco AI Defense Inspection API vs Mistral Moderation API](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-mistral-moderation.md)\n- [Cisco AI Defense Inspection API vs OpenAI Moderation API](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-openai-moderation.md)\n- [Google Cloud Model Armor vs ShieldGemma](https://www.anchorterminal.com/compare/google-model-armor-vs-shieldgemma.md)\n- [Granite Guardian vs ShieldGemma](https://www.anchorterminal.com/compare/granite-guardian-vs-shieldgemma.md)\n- [Guardrails AI vs ShieldGemma](https://www.anchorterminal.com/compare/guardrails-ai-vs-shieldgemma.md)\n- [Lakera Guard (Check Point AI Guardrails) vs ShieldGemma](https://www.anchorterminal.com/compare/lakera-guard-vs-shieldgemma.md)\n- [Llama Guard 4 vs ShieldGemma](https://www.anchorterminal.com/compare/llama-guard-vs-shieldgemma.md)\n- [Mistral Moderation API vs ShieldGemma](https://www.anchorterminal.com/compare/mistral-moderation-vs-shieldgemma.md)\n- [NVIDIA NeMo Guardrails vs ShieldGemma](https://www.anchorterminal.com/compare/nemo-guardrails-vs-shieldgemma.md)\n- [OpenAI Guardrails vs ShieldGemma](https://www.anchorterminal.com/compare/openai-guardrails-vs-shieldgemma.md)\n- [OpenAI Moderation API vs ShieldGemma](https://www.anchorterminal.com/compare/openai-moderation-vs-shieldgemma.md)\n- [Prisma AIRS AI Runtime Security API vs ShieldGemma](https://www.anchorterminal.com/compare/prisma-airs-vs-shieldgemma.md)\n- [Amazon Bedrock Guardrails vs Cisco AI Defense Inspection API](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-cisco-ai-defense-inspection.md)\n- [Azure AI Content Safety (Prompt Shields) vs Cisco AI Defense Inspection API](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-cisco-ai-defense-inspection.md)\n- [Cisco AI Defense Inspection API vs Google Cloud Model Armor](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-google-model-armor.md)\n- [Cisco AI Defense Inspection API vs Granite Guardian](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-granite-guardian.md)\n- [Cisco AI Defense Inspection API vs Guardrails AI](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-guardrails-ai.md)\n- [Cisco AI Defense Inspection API vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-lakera-guard.md)\n- [Cisco AI Defense Inspection API vs LlamaFirewall](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llamafirewall.md)\n- [Cisco AI Defense Inspection API vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-nemo-guardrails.md)\n- [Cisco AI Defense Inspection API vs OpenAI Guardrails](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-openai-guardrails.md)\n- [Cisco AI Defense Inspection API vs Prisma AIRS AI Runtime Security API](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-prisma-airs.md)\n- [AgentGate vs Cisco AI Defense Inspection API](https://www.anchorterminal.com/compare/agentgate-vs-cisco-ai-defense-inspection.md)\n- [AgentGate vs ShieldGemma](https://www.anchorterminal.com/compare/agentgate-vs-shieldgemma.md)\n- [LlamaFirewall vs ShieldGemma](https://www.anchorterminal.com/compare/llamafirewall-vs-shieldgemma.md)\n- [Cisco AI Defense Inspection API vs Presidio](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-microsoft-presidio.md)\n- [Presidio vs ShieldGemma](https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cisco AI Defense Inspection API vs ShieldGemma", "url": "" } ], "description": "Cisco AI Defense Inspection scores 63.1 (B) to ShieldGemma's 54 (C) for content moderation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cisco AI Defense Inspection API B 63.1", "ShieldGemma C 54", "scores" ], "h1": "Cisco AI Defense Inspection API vs ShieldGemma", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cisco-ai-defense-inspection-vs-shieldgemma", "published": "2026-10-01", "section": "tools", "title": "Cisco AI Defense Inspection vs ShieldGemma for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma" }, "tokens": { "markdown": 6100, "slim": 3680 }, "version": 1 }