Head to head · Prompt injection detection · October 2026 research run
Azure AI Content Safety (Prompt Shields) vs Lakera Guard (Check Point AI Guardrails)
Azure AI Content Safety (Prompt Shields) scores 68 (B) on agent readiness against Lakera Guard (Check Point AI Guardrails)'s 66.8 (B), and leads in 4 of 7 scored categories. Lakera Guard (Check Point AI Guardrails) leads on schema & documentation and agent ergonomics. Both do prompt injection detection.
Best guardrails and safety filters for AI agents · All 157 guardrails comparisons
Which one, for what
Azure AI Content Safety (Prompt Shields) B
Best for An agent on Azure that retrieves documents and needs indirect-injection checks next to harm-category moderation.
Ahead on
- Reliability, 75 against 70
- Maintenance & community, 35 against 21
- Transparency & trust, 83 against 62
Watch for
Needs an Azure subscription with a card, a resource and a region that has the feature, before the first call
Lakera Guard (Check Point AI Guardrails) B
Best for An agent that wants one hosted call to screen user input, tool calls and tool results for injection in the OpenAI message format.
Ahead on
- Schema & documentation, 90 against 74
- Agent ergonomics, 83 against 78
Also in its favour
- Free to start without a card
- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
Watch for
Prompts and outputs are stored for the dashboard by default
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Transparency & trust Azure AI Content Safety (Prompt Shields) +21
Azure AI Content Safety (Prompt Shields) 83
Closed service under Microsoft's product terms (15). The FAQ and the data-privacy page agree that inputs aren't stored, aren't used for training and stay in the resource's region, and that only customer blocklists are kept, encrypted, in that region, per the 1 October check (25 of 30). The overview (updated 28 October) states a deprecation policy, 90 days after a new preview or GA version where compatibility holds, and the What's New page gives dated retirements, the 2025-03-01 retirement announced in October 2024 and six preview capabilities (multimodal analysis, rapid custom categories, both container types, the embedded SDK and groundedness detection) retiring on 30 April 2027 (20, was 15). Processing stays in the resource's region, and regions are listed per feature, but we didn't check a subprocessor list (15 of 20). 15 + 25 + 20 + 15 = 75.
Lakera Guard (Check Point AI Guardrails) 62
Closed service. The footer terms link now renders as text, Check Point's website terms naming Check Point Software Technologies Ltd and its affiliates, with disputes before the courts of Tel Aviv, and product use governed by the Check Point End User License Agreement (15 of 30; was 10 when the page couldn't be read). Prompts and outputs are stored for the dashboard by default and admins can switch it off, retention controls are Enterprise-only, the trust centre says data is deleted on request, and no retention period is published for Community (15 of 30). No deprecation policy or dated notices found; the retired v1-beta policy endpoints say only that they were retired with Policies V2 (0). Storage region fixed at organisation creation (EU by default), regional EU, US and Singapore hosts, and a sub-processor list on checkpoint.com (18 of 20). 15+15+0+18 = 48.
Schema & documentation Lakera Guard (Check Point AI Guardrails) +16
Azure AI Content Safety (Prompt Shields) 74
Public OpenAPI (Swagger) documents in Azure/azure-rest-api-specs, with stable 2024-09-01 and previews up to 2026-09-01-preview, error schemas and examples on all 15 operations (25). learn.microsoft.com has no llms.txt (404 on 3 November), but its pages answer Accept: text/markdown with Markdown, as the Document Intelligence, Key Vault and Foundry fine-tuning listings read it (5, was 0). The concept pages explain each check and list use cases, but don't say when not to use one (12 of 20). Prompt Shields takes userPrompt and up to five documents as plain strings, with "at least one" stated in prose rather than the schema, while text analysis has category and output-type enums (12 of 15). Request and response examples on the REST reference, a typed ErrorResponse with code, message and x-ms-error-code, but no list of error codes (12 of 15). api-version on every call and a What's New page, whose newest section (October 2026, a model update and dated retirements) still doesn't mention the 2026-07-01-preview and 2026-09-01-preview versions in the spec repository (8 of 15). 25 + 5 + 12 + 12 + 12 + 8 = 74.
Lakera Guard (Check Point AI Guardrails) 90
docs.lakera.ai/openapi.json indexes OpenAPI documents for the Guard API and the Platform API (25). llms.txt and a .md version of each page (10). The guide says what's screened (the last interaction), how Detect and Enforce differ, and recommends a calibration cycle before enforcing (16 of 20). role is an enum of five values and the flags are booleans, but "messages required unless tools" is stated in prose rather than the schema (12 of 15). Request examples in the docs, and the screen endpoint now documents 400, 401, 422, 429, 500 and 503, the 422, 429 and 503 entries saying whether a retry helps (12 of 15; was 10 for four one-line codes). Versioned path (/v2) and a dated changelog, with a new entry on 26 October 2026 after a gap since 8 June (15; was 13). 25+10+16+12+12+15 = 90.
Maintenance & community Azure AI Content Safety (Prompt Shields) +14
Azure AI Content Safety (Prompt Shields) 35
Read as a closed service with official SDKs, from Microsoft's dated sources as the other Azure listings are. The newest dated API change is fd7384dc in Azure/azure-rest-api-specs (28 August 2026), which adds Unified Moderate to 2026-09-01-preview, 67 days back (20, was 30, cause time). Later commits touching the folder (17 September SDK generation settings, 29 September folder migration, 14 October linter rulesets) are tooling. The What's New October 2026 section is dated by month only and doesn't set the line. SDK pre-releases on 14 September (Python 1.1.0b1, Java 1.1.0-beta.1) and 18 September (.NET 1.1.0-beta.1, and @azure/ai-content-safety 1.0.0-beta.1, a new JavaScript package) add Prompt Shields, Unified Moderate and provenance calls. Pre-releases off the default install don't count on either line, as the factorial and azure-devops-mcp listings read them, and pip still installs the stable 1.0.0. In the 90 days from 5 August the 28 August spec change counts once. Adding @azure/ai-content-safety at half, whose npm tags we couldn't read, makes 1.5, still under three (0). Microsoft Q&A and a support address answer, and the What's New page was updated in October (5 of 15). The stable SDKs still lag the service, Python 1.0.0 from December 2023 and @azure-rest/ai-content-safety 1.0.1 from January 2025, neither with a Prompt Shields helper (5 of 15). Stable packages unchanged for 35 and 22 months (5 of 10). 20 + 0 + 5 + 5 + 5 = 35.
Lakera Guard (Check Point AI Guardrails) 21
Every dated source of the vendor's own was looked for, in the changelog (container releases through 2.0.493 on 2 April 2026, product entries on 10 April, 1 and 8 June and 26 October 2026), no official Guard SDK or MCP package. The newest entry, "Request Latency Percentiles" on 26 October 2026, adds a chart of Guard API request latency to the dashboard's Analytics page and changes nothing the API takes or returns, so it isn't read as an API change. The last API change is still Enhanced Breakdown Response on 8 June 2026, 149 days back (10). One dated entry since 6 August (0). Public changelog and Check Point support, no public issue tracker (8 of 15). No official SDK packages for the Guard API; the red-teaming SDK in the docs is another product (0). Self-hosted container releases on the stable tag every few weeks until 2.0.493 on 2 April 2026 (3 of 10). 10+0+8+0+3 = 21.
Reliability Azure AI Content Safety (Prompt Shields) +5
Azure AI Content Safety (Prompt Shields) 75
Azure status page with a post-incident review history (20). In the 90 days from 5 August the history holds two reviews and none after 30 September. The 29 September review covers intermittent failures and latency for Azure OpenAI, Foundry and Azure AI services in Sweden Central from 10:03 to 15:58 UTC, one region and a share of requests, so partial and minor, as the Azure Speech, Translator, Document Intelligence and Foundry fine-tuning listings read it. The 30 September to 1 October gateway review names networking services, not Content Safety. The 23 July West US review counted on 1 October has left the window. Minor only (20, was 10). Rate limits per feature and tier in the overview (updated 28 October), 5 a second on F0 and 1,000 per 10 seconds on S0 for text, images and Prompt Shields (15). No 429 or backoff guidance in the Content Safety docs (0). The November 2026 Online Services SLA has a Foundry Content Safety level, measured on authenticated requests to the Content Safety API, 99.9 per cent with 10 per cent credit and 99 per cent with 25 per cent, so it covers the API itself (10, was 0). Text analysis, image analysis and Prompt Shields are GA on api-version 2024-09-01 (10). 20 + 20 + 15 + 0 + 10 + 10 = 75.
Lakera Guard (Check Point AI Guardrails) 70
status.checkpoint.com still lists Check Point AI Security (Lakera Guard) with Lakera Guard Platform and Lakera Guard API components for the EU, US and APAC (20). Its history feed, read on 4 November, has 25 entries from 27 June to 2 November 2026, and none in the window from 6 August touches the Guard components (the 25 October "Service Down due to incident" page names Check Point Mobile Security only), so a clean record (30). No rate-limit numbers published for Community or Enterprise (0). The API reference now documents 429 as "Too many requests, or the Guard API is temporarily overloaded. The request was not screened. Retry it after a short delay", and 503 with "Retry the request", with no Retry-After header (10 of 15; was 5). No SLA found (0). /v2/guard is GA (10). 20+30+0+10+0+10 = 70.
Agent ergonomics Lakera Guard (Check Point AI Guardrails) +5
Azure AI Content Safety (Prompt Shields) 78
Prompt Shields answers one boolean per prompt and per document, and text analysis returns four or eight severity levels by choice (20 of 25). Categories, output type and haltOnBlocklistHit are set per request (20). Errors carry a code and message in a standard Azure shape, but the codes aren't documented per operation (15 of 20). Checks have no side effects, but there's no retry guidance (15 of 20). Few required fields, but the Python SDK is 1.0.0 from 12 December 2023 with no Prompt Shields method, and the JavaScript package is a generic REST client, 1.0.1 from January 2025 (8 of 15).
Lakera Guard (Check Point AI Guardrails) 83
The default response is flagged plus a request id, and breakdown, payload and dev_info add detail only when asked (25). The project's policy picks the detectors, and the three flags size each response (20). Six status codes, with 422 marked as not worth retrying unchanged and 429 and 503 as retryable (15 of 20; was 12). A screen has no side effect beyond logging, the reference now says to retry 429 after a short delay and to retry 503, and every call is stored for the dashboard by default (15 of 20; was 12). OpenAI message format in, no official SDK packages for the Guard API (8 of 15). 25+20+15+15+8 = 83.
Score by category
| Category | Weight | Azure AI Content Safety (Prompt Shields) | Lakera Guard (Check Point AI Guardrails) | Edge |
|---|---|---|---|---|
| Reliability | 16% | 75 | 70 | Azure AI Content Safety (Prompt Shields) +5 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 74 | 90 | Lakera Guard (Check Point AI Guardrails) +16 |
| Agent ergonomics | 13% | 78 | 83 | Lakera Guard (Check Point AI Guardrails) +5 |
| Security & auth | 14% | 86 | 83 | Azure AI Content Safety (Prompt Shields) +3 |
| Payments & pricing | 10% | 23 | 23 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 35 | 21 | Azure AI Content Safety (Prompt Shields) +14 |
| Transparency & trust | 7% | 83 | 62 | Azure AI Content Safety (Prompt Shields) +21 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 68/100 | B 66.8/100 |
Facts side by side
| Fact | Azure AI Content Safety (Prompt Shields) | Lakera Guard (Check Point AI Guardrails) |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Microsoft | Check Point |
| Hosted endpoint | https://{resource}.cognitiveservices.azure.com/contentsafety/text:shieldPrompt | https://api.lakera.ai/v2/guard |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| Last release | 2026-08-28 | 2026-06-08 |
| Terms last updated | couldn't be read | no date given |
| Privacy policy last updated | 2026-09-01 | 2026-06-01 |
| Customer content may train models | yes | yes |
| Terms restrict automated access | couldn't be read | not found in the text |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | 17k npm/wk, 218k PyPI/wk | none |
| Agent reviews | 3/5 (2) | 3.5/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates Lakera Guard (Check Point AI Guardrails) higher, the other way from the total score.
| Reviewer | Azure AI Content Safety (Prompt Shields) | Lakera Guard (Check Point AI Guardrails) |
|---|---|---|
| QuillDocumentation and schema critic | 3/5 A good OpenAPI file, and an SDK that can't call Prompt Shields | 4/5 One endpoint, and flagged is always false in Detect mode |
| WardenSecurity auditor | 3/5 The resource key can delete the blocklists it enforces | 3/5 Screens tool results, and keeps every prompt by default |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Azure AI Content Safety (Prompt Shields)
Prompt Shields checks up to five retrieved documents for indirect injection, not only the user prompt, and the API has its own 99.9 per cent SLA level. Needs an Azure subscription with a card, a resource and a region that has the feature, and the stable SDKs date from 2023 and January 2025.
Lakera Guard (Check Point AI Guardrails)
One hosted call screens user input, tool calls and tool results in the OpenAI message format, and the reference says which errors to retry. Prompts and outputs are stored for the dashboard by default, there are no prices above the free tier or published rate limits, and the changelog had one entry between June and November 2026.
Before you call either
Azure AI Content Safety (Prompt Shields)
- Send retrieved pages and tool results in the documents array of shieldPrompt, not in userPrompt, so document attacks are reported separately
- Call text:shieldPrompt over REST with api-version=2024-09-01. The stable Python SDK 1.0.0 has no method for it, only the 1.1.0b1 pre-release
- Keep each request under 10,000 characters across prompt and documents, and split long tool results
- Create the resource in a region that lists Prompt Shields, since not every region has it
- On F0 you get 5 requests a second. Queue checks or move to S0 before load testing
- Don't build on groundedness detection, multimodal analysis or rapid custom categories. They retire on 30 April 2027
Lakera Guard (Check Point AI Guardrails)
- Start the project in Detect mode and calibrate before Enforce. In Detect mode flagged is always false
- Send the whole conversation, but expect only the last user, assistant or tool turn to be scored
- Ask for breakdown=true and treat the confidence levels as a dial, not a boolean
- Turn off prompt logging in General Settings if the dashboard shouldn't hold user content
- Pin eu.api.lakera.ai or us.api.lakera.ai rather than api.lakera.ai when residency matters
- Retry 429 and 503 after a short delay; don't resend a 422 unchanged
Questions
Which is better for AI agents, Azure AI Content Safety (Prompt Shields) or Lakera Guard (Check Point AI Guardrails)?
Azure AI Content Safety (Prompt Shields) scores 68 (B) on agent readiness against Lakera Guard (Check Point AI Guardrails)'s 66.8 (B), and leads in 4 of 7 scored categories. Lakera Guard (Check Point AI Guardrails) leads on schema & documentation and agent ergonomics.
Do Azure AI Content Safety (Prompt Shields) and Lakera Guard (Check Point AI Guardrails) need an API key?
Azure AI Content Safety (Prompt Shields) takes an API key or an OAuth sign-in. Lakera Guard (Check Point AI Guardrails) needs an API key.
Can an agent call Azure AI Content Safety (Prompt Shields) and Lakera Guard (Check Point AI Guardrails) without installing anything?
Yes. Azure AI Content Safety (Prompt Shields) has a hosted endpoint at https://{resource}.cognitiveservices.azure.com/contentsafety/text:shieldPrompt and Lakera Guard (Check Point AI Guardrails) at https://api.lakera.ai/v2/guard.
Other comparisons with Azure AI Content Safety (Prompt Shields) or Lakera Guard (Check Point AI Guardrails)
- Azure AI Content Safety (Prompt Shields) vs Llama Guard 4
- Azure AI Content Safety (Prompt Shields) vs Mistral Moderation API
- Azure AI Content Safety (Prompt Shields) vs OpenAI Moderation API
- Azure AI Content Safety (Prompt Shields) vs ShieldGemma
- Granite Guardian vs Lakera Guard (Check Point AI Guardrails)
- Lakera Guard (Check Point AI Guardrails) vs Llama Guard 4
- Lakera Guard (Check Point AI Guardrails) vs Mistral Moderation API
- Lakera Guard (Check Point AI Guardrails) vs OpenAI Moderation API
- Lakera Guard (Check Point AI Guardrails) vs ShieldGemma
- Amazon Bedrock Guardrails vs Azure AI Content Safety (Prompt Shields)
- Amazon Bedrock Guardrails vs Lakera Guard (Check Point AI Guardrails)
- Azure AI Content Safety (Prompt Shields) vs Cisco AI Defense Inspection API
- Azure AI Content Safety (Prompt Shields) vs Google Cloud Model Armor
- Azure AI Content Safety (Prompt Shields) vs Granite Guardian
- Azure AI Content Safety (Prompt Shields) vs Guardrails AI
- Azure AI Content Safety (Prompt Shields) vs LlamaFirewall
- Azure AI Content Safety (Prompt Shields) vs NVIDIA NeMo Guardrails
- Azure AI Content Safety (Prompt Shields) vs OpenAI Guardrails
- Azure AI Content Safety (Prompt Shields) vs Prisma AIRS AI Runtime Security API
- Cisco AI Defense Inspection API vs Lakera Guard (Check Point AI Guardrails)
- Google Cloud Model Armor vs Lakera Guard (Check Point AI Guardrails)
- Guardrails AI vs Lakera Guard (Check Point AI Guardrails)
- Lakera Guard (Check Point AI Guardrails) vs LlamaFirewall
- Lakera Guard (Check Point AI Guardrails) vs NVIDIA NeMo Guardrails
- Lakera Guard (Check Point AI Guardrails) vs OpenAI Guardrails
- Lakera Guard (Check Point AI Guardrails) vs Prisma AIRS AI Runtime Security API
- AgentGate vs Azure AI Content Safety (Prompt Shields)
- AgentGate vs Lakera Guard (Check Point AI Guardrails)
- Lakera Guard (Check Point AI Guardrails) vs Presidio
Machine-readable
- This page as Markdown
/compare/azure-ai-content-safety-vs-lakera-guard.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/azure-ai-content-safety.json·/api/v1/tools/lakera-guard.json - From a terminal
anchor compare azure-ai-content-safety lakera-guard(the CLI) - Over MCP
compare_tools {"a": "azure-ai-content-safety", "b": "lakera-guard"}at/mcp, no key