{
  "fixes": {
    "slug": "agent-zero",
    "name": "Agent Zero",
    "listing": "https://www.anchorterminal.com/tools/agent-zero",
    "markdown": "# Fix list: Agent Zero\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/agent-zero, the October 2026 research run, assessed 12 October 2026. Grade C, 54.2 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Agent Zero: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Reliability, 57 out of 100, up to 8.6 more on the total\n\nWhy it scored 57: Read with the local-software lines, as software the owner runs. Installs from the `agent0ai/agent-zero` Docker image, an install script, or a desktop Launcher with builds for macOS, Linux and Windows on x86 and ARM64. The README says it runs wherever Docker runs. The image registry page was not read (17 of 20). The repository holds 191 test files, and its only two workflows publish Docker images and close inactive issues, so no public CI run shows the tests passing (5 of 25). 139 open issues and pull requests on 12 October 2026. Open reports from September include a crash of `run_ui` after a failed memory consolidation (#1909), a browser worker that hangs the agent turn (#1923) and truncated backups (#1904), each with no reply or one, and a workflow closes anything inactive for 90 days (11 of 25). Release notes for v2.11, v2.12 and v2.13 carry a Breaking Changes section, but breaking changes ship in minor versions, so the numbering is not semver (9 of 15). v2.13, past 1.0 (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Security \u0026 auth, 54 out of 100, up to 8.1 more on the total\n\nWhy it scored 54: Harness reading of the framework checklist, the one the Goose calibration dossier uses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No usage telemetry was found in the source. An update check, on by default, posts the version and a 20-character hash of the instance id to api.agent-zero.ai, and one setting turns it off. The reviewed docs do not describe what it sends (22). The agent works inside a Docker container built on Kali Linux and runs as root there. Tool Access can block tools by project or profile and defaults to allow, host access through the A0 CLI is scoped by read, write and execute permissions, and no approval step was found before a shell command, a file deletion or an outgoing message. The web interface has no login until a username is set (10). Infection Check audits the agent's reasoning with a second model before each tool call and ships disabled. Scanners check plugins, skills and MCP servers before install. The channel allow-lists accept every sender when empty, and the email filter matches the claimed From address only, which the plugin README states (7). Chat logs, visible tool steps and Time Travel snapshots, with no per-call audit log. Per-process log files were removed in v2.5 (9). No SECURITY.md, security.txt answered 404, and the repository has no published advisory, while NVD lists five CVEs since March 2026. A security-review ledger in the repository records two findings, and the v2.12 notes name both fixes (6).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 3. Agent ergonomics, 62 out of 100, up to 6.2 more on the total\n\nWhy it scored 62: Harness reading, scored on what a person or program driving it must supply. Skills load on demand, blocked tools are removed from the prompt, chats can be compacted, and the v2.12 notes report Codex input falling from about 16.4K to 11.3K tokens, a vendor figure (18 of 25). An MCP tool timeout of 120 seconds, a limit of five consecutive unusable responses and context-window handling are set by default. No turn or spend limit was found in the reviewed docs (11 of 20). Other programs reach it through `POST /api_message`, an optional MCP server, A2A and an ACP bridge, with request and response shapes left to the source (11 of 20). An error-retry plugin, saved chats, a message queue, backups and Time Travel snapshots with diff and revert (14 of 20). One Docker command starts it and a wizard sets the model, but there is no SDK and the default has no login (8 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 4. Schema \u0026 documentation, 64 out of 100, up to 5.9 more on the total\n\nWhy it scored 64: Harness reading of the lines, as the Goose calibration dossier does. No OpenAPI file. The connectivity page lists five external endpoints and the `X-API-KEY` header, then sends readers to the source or DeepWiki for request and response details. Each API handler and tool has a `.dox.md` contract file in the repository, and the MCP client JSON shape is documented (10 of 25). llms.txt at www.agent-zero.ai, and AGENTS.md contract files across the repository (10). Guides say which path to use for a need, with tables that separate the browser, the host connector, MCP and A2A (14 of 20). The v2.12 notes say 15 bundled tools gained argument descriptions in non-strict schemas, and plugin settings are typed YAML with commented examples (8 of 15). Guides carry worked examples and a troubleshooting page, with no documented error responses for the external API (9 of 15). Dated notes on every GitHub release and a release article for each version on the site, with no version prefix on API routes (13 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 5. Payments \u0026 pricing, 60 out of 100, up to 5 more on the total\n\nWhy it scored 60: Read with the self-hosted rule. No payment protocol in the source (0). Free under MIT with nothing to buy for the software, so 20, 20 and 20 on the last three lines. It starts with one Docker command and no account. Model usage is billed by whichever provider the owner configures, or costs nothing with a local model. The vendor's site also describes a beta LLM API whose daily quota depends on staking its A0T token. That is separate from the software and not scored.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 6. Transparency \u0026 trust, 55 out of 100, up to 3.9 more on the total\n\nMade of editorial 56, provenance 53.\n\nWhy it scored 55: MIT, copyright Agent Zero, s.r.o. (30). No privacy policy for the software was found. The site's cookie notice covers the website, and its terms cover the community platform. The docs say where data lives (chats, memory, secrets and settings under `/a0/usr`) and warn that model providers see what is sent to them only in general terms, with no retention statement (8 of 30). Release notes list breaking changes and removals with the release date, and one deprecated alias is named. No deprecation policy or notice period was found (8 of 20). No telemetry was found, and the update check has an off switch in settings, but what it sends is not described in the reviewed docs (10 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: agent-zero.ai, no registry record we could read (0 of 15)\n- Status page: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Maintenance \u0026 community, 75 out of 100, up to 2.2 more on the total\n\nWhy it scored 75: v2.13 was published on 23 September 2026, 19 days before this check (30). Nine releases since 14 July 2026, v2.5 to v2.13 (20). Of the 40 newest open items read on 12 October, 16 are issues and 14 of those have no comment. Three security reports filed as issues were closed as completed, one in five days and two after three months (10 of 25). The Docker image, the desktop Launcher, the install scripts and the A0 CLI connector come from the same organisation, and the README links Launcher 1.8 (10 of 15). A Docker publish workflow builds images from tags, and the v2.0 notes record a LiteLLM upgrade past a patched CVE floor. No public test CI (5 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 2026-03-17. CVE-2026-4307 (path traversal in `get_abs_path`, CVSS 4.3) and CVE-2026-4308 (server-side request forgery in document queries, CVSS 6.3), both against 0.9.7, with public exploits. The NVD entries say the vendor was contacted and did not respond. The v2.9 notes of 12 August 2026 list a fix for an SSRF regression under CVE-2026-4308. Whether CVE-2026-4307 is fixed was not established. -2. https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=CVE-2026-4308\n- 2026-05-27. CVE-2026-47119, stored cross-site scripting through SVG files served by the `image_get` endpoint, CVSS 6.1, in versions before 1.15. The report (#1609) was closed as completed on 12 May 2026. Fixed, and no GitHub advisory was published. -1. https://github.com/agent0ai/agent-zero/issues/1609\n- 2026-09-30. CVE-2026-51852 and CVE-2026-51853, directory traversal in the file browser of versions 1.7 to 1.10, CVSS 7.5 each. Reported as issues #1539 and #1540 on 20 April 2026 and closed as completed on 24 July 2026. The file browser still starts at the container root by design. -1. https://github.com/agent0ai/agent-zero/issues/1540\n- 2026-09-09. Two flaws recorded in the project's own security-review ledger and fixed in v2.12 the same day. An unauthenticated Telegram webhook accepted forged updates, and WhatsApp document names could overwrite files outside the media cache before the sender check ran. The ledger rates both high. Named in the release notes, with no advisory. -2. https://github.com/agent0ai/agent-zero/blob/main/security-review/LEDGER.md\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- Fit. Agent Zero's README calls it an open agent framework and a Linux workbench, and its use cases are software, research and office files. It is a general agent framework with messaging channels, a scheduler and memory, not a product built as a personal assistant. It has no built-in calendar or contacts connection\n- Kind. Recorded as `harness`, the closest kind the briefs define for an agent program the owner runs, with `metrics.kind` local\n- `assistant.accounts` is claimed only for the mailbox the email integration signs in to with a username and password. Anything else is reached through MCP servers or stored secrets\n- unchecked: whether CVE-2026-4307 is fixed, and the release date of 1.15, which the shallow clone and the 15 releases read do not cover\n- unchecked: the private report GHSA-q4mh-57gh-36r2 that issue #1609 cites. The repository's advisory list is empty, so its outcome is unknown\n- unchecked: the Docker image registry page, so image tags, architectures and pull counts are unconfirmed\n- unchecked: whether the tests pass today. No public CI runs them\n- unchecked: the registration date of agent-zero.ai, the MCP registry, the Launcher, installer and A0 CLI repositories, and the site's docs pages other than secrets\n- unchecked: where the Telegram, WhatsApp and email settings are encrypted, if anywhere. The source stores plugin settings as `config.json` and secrets as `secrets.env` under `/a0/usr`\n- The GitHub API reports the licence as NOASSERTION because the file adds contact lines. Its text is the MIT licence\n- The repository's last push was 11 October 2026, while main's last commit is 23 September, so current work sits on other branches\n- Researched as a candidate for the personal assistants category and listed under agent harnesses, because its README calls it an agent framework and Linux workbench and its messaging channels, scheduler and memory are plugins.\n\n## Weaknesses\n\n- No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow\n- The web interface has no login until the owner sets a username, and the README command publishes port 80\n- Five CVEs published between 17 March and 30 September 2026, none as a GitHub advisory, and no SECURITY.md or security.txt\n- Infection Check, the prompt-injection audit before tool calls, ships turned off\n- Empty allow-lists in the Telegram, WhatsApp and email integrations accept messages from anyone\n- No public CI runs the 191 test files. The only workflows publish Docker images and close inactive issues\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none\n- Fill `allowed_users`, `allowed_numbers` or `sender_whitelist` before enabling a channel. An empty list accepts every sender\n- Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled\n- Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal\n- Call `POST /api_message` with the `X-API-KEY` header. The token changes when the UI login or password changes\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "C",
    "score": 54.2,
    "assessed": "2026-10-12",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 57,
        "maxGain": 8.6,
        "reason": "Read with the local-software lines, as software the owner runs. Installs from the `agent0ai/agent-zero` Docker image, an install script, or a desktop Launcher with builds for macOS, Linux and Windows on x86 and ARM64. The README says it runs wherever Docker runs. The image registry page was not read (17 of 20). The repository holds 191 test files, and its only two workflows publish Docker images and close inactive issues, so no public CI run shows the tests passing (5 of 25). 139 open issues and pull requests on 12 October 2026. Open reports from September include a crash of `run_ui` after a failed memory consolidation (#1909), a browser worker that hangs the agent turn (#1923) and truncated backups (#1904), each with no reply or one, and a workflow closes anything inactive for 90 days (11 of 25). Release notes for v2.11, v2.12 and v2.13 carry a Breaking Changes section, but breaking changes ship in minor versions, so the numbering is not semver (9 of 15). v2.13, past 1.0 (15).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 54,
        "maxGain": 8.1,
        "reason": "Harness reading of the framework checklist, the one the Goose calibration dossier uses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No usage telemetry was found in the source. An update check, on by default, posts the version and a 20-character hash of the instance id to api.agent-zero.ai, and one setting turns it off. The reviewed docs do not describe what it sends (22). The agent works inside a Docker container built on Kali Linux and runs as root there. Tool Access can block tools by project or profile and defaults to allow, host access through the A0 CLI is scoped by read, write and execute permissions, and no approval step was found before a shell command, a file deletion or an outgoing message. The web interface has no login until a username is set (10). Infection Check audits the agent's reasoning with a second model before each tool call and ships disabled. Scanners check plugins, skills and MCP servers before install. The channel allow-lists accept every sender when empty, and the email filter matches the claimed From address only, which the plugin README states (7). Chat logs, visible tool steps and Time Travel snapshots, with no per-call audit log. Per-process log files were removed in v2.5 (9). No SECURITY.md, security.txt answered 404, and the repository has no published advisory, while NVD lists five CVEs since March 2026. A security-review ledger in the repository records two findings, and the v2.12 notes name both fixes (6).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 62,
        "maxGain": 6.2,
        "reason": "Harness reading, scored on what a person or program driving it must supply. Skills load on demand, blocked tools are removed from the prompt, chats can be compacted, and the v2.12 notes report Codex input falling from about 16.4K to 11.3K tokens, a vendor figure (18 of 25). An MCP tool timeout of 120 seconds, a limit of five consecutive unusable responses and context-window handling are set by default. No turn or spend limit was found in the reviewed docs (11 of 20). Other programs reach it through `POST /api_message`, an optional MCP server, A2A and an ACP bridge, with request and response shapes left to the source (11 of 20). An error-retry plugin, saved chats, a message queue, backups and Time Travel snapshots with diff and revert (14 of 20). One Docker command starts it and a wizard sets the model, but there is no SDK and the default has no login (8 of 15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 64,
        "maxGain": 5.9,
        "reason": "Harness reading of the lines, as the Goose calibration dossier does. No OpenAPI file. The connectivity page lists five external endpoints and the `X-API-KEY` header, then sends readers to the source or DeepWiki for request and response details. Each API handler and tool has a `.dox.md` contract file in the repository, and the MCP client JSON shape is documented (10 of 25). llms.txt at www.agent-zero.ai, and AGENTS.md contract files across the repository (10). Guides say which path to use for a need, with tables that separate the browser, the host connector, MCP and A2A (14 of 20). The v2.12 notes say 15 bundled tools gained argument descriptions in non-strict schemas, and plugin settings are typed YAML with commented examples (8 of 15). Guides carry worked examples and a troubleshooting page, with no documented error responses for the external API (9 of 15). Dated notes on every GitHub release and a release article for each version on the site, with no version prefix on API routes (13 of 15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 60,
        "maxGain": 5,
        "reason": "Read with the self-hosted rule. No payment protocol in the source (0). Free under MIT with nothing to buy for the software, so 20, 20 and 20 on the last three lines. It starts with one Docker command and no account. Model usage is billed by whichever provider the owner configures, or costs nothing with a local model. The vendor's site also describes a beta LLM API whose daily quota depends on staking its A0T token. That is separate from the software and not scored.",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 55,
        "maxGain": 3.9,
        "reason": "MIT, copyright Agent Zero, s.r.o. (30). No privacy policy for the software was found. The site's cookie notice covers the website, and its terms cover the community platform. The docs say where data lives (chats, memory, secrets and settings under `/a0/usr`) and warn that model providers see what is sent to them only in general terms, with no retention statement (8 of 30). Release notes list breaking changes and removals with the release date, and one deprecated alias is named. No deprecation policy or notice period was found (8 of 20). No telemetry was found, and the update check has an off switch in settings, but what it sends is not described in the reviewed docs (10 of 20).",
        "blend": "editorial 56, provenance 53",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 75,
        "maxGain": 2.2,
        "reason": "v2.13 was published on 23 September 2026, 19 days before this check (30). Nine releases since 14 July 2026, v2.5 to v2.13 (20). Of the 40 newest open items read on 12 October, 16 are issues and 14 of those have no comment. Three security reports filed as issues were closed as completed, one in five days and two after three months (10 of 25). The Docker image, the desktop Launcher, the install scripts and the A0 CLI connector come from the same organisation, and the README links Launcher 1.8 (10 of 15). A Docker publish workflow builds images from tags, and the v2.0 notes record a LiteLLM upgrade past a patched CVE floor. No public test CI (5 of 10).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "agent-zero.ai, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "2026-03-17. CVE-2026-4307 (path traversal in `get_abs_path`, CVSS 4.3) and CVE-2026-4308 (server-side request forgery in document queries, CVSS 6.3), both against 0.9.7, with public exploits. The NVD entries say the vendor was contacted and did not respond. The v2.9 notes of 12 August 2026 list a fix for an SSRF regression under CVE-2026-4308. Whether CVE-2026-4307 is fixed was not established. -2. https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=CVE-2026-4308",
      "2026-05-27. CVE-2026-47119, stored cross-site scripting through SVG files served by the `image_get` endpoint, CVSS 6.1, in versions before 1.15. The report (#1609) was closed as completed on 12 May 2026. Fixed, and no GitHub advisory was published. -1. https://github.com/agent0ai/agent-zero/issues/1609",
      "2026-09-30. CVE-2026-51852 and CVE-2026-51853, directory traversal in the file browser of versions 1.7 to 1.10, CVSS 7.5 each. Reported as issues #1539 and #1540 on 20 April 2026 and closed as completed on 24 July 2026. The file browser still starts at the container root by design. -1. https://github.com/agent0ai/agent-zero/issues/1540",
      "2026-09-09. Two flaws recorded in the project's own security-review ledger and fixed in v2.12 the same day. An unauthenticated Telegram webhook accepted forged updates, and WhatsApp document names could overwrite files outside the media cache before the sender check ran. The ledger rates both high. Named in the release notes, with no advisory. -2. https://github.com/agent0ai/agent-zero/blob/main/security-review/LEDGER.md"
    ],
    "unchecked": [
      "Fit. Agent Zero's README calls it an open agent framework and a Linux workbench, and its use cases are software, research and office files. It is a general agent framework with messaging channels, a scheduler and memory, not a product built as a personal assistant. It has no built-in calendar or contacts connection",
      "Kind. Recorded as `harness`, the closest kind the briefs define for an agent program the owner runs, with `metrics.kind` local",
      "`assistant.accounts` is claimed only for the mailbox the email integration signs in to with a username and password. Anything else is reached through MCP servers or stored secrets",
      "unchecked: whether CVE-2026-4307 is fixed, and the release date of 1.15, which the shallow clone and the 15 releases read do not cover",
      "unchecked: the private report GHSA-q4mh-57gh-36r2 that issue #1609 cites. The repository's advisory list is empty, so its outcome is unknown",
      "unchecked: the Docker image registry page, so image tags, architectures and pull counts are unconfirmed",
      "unchecked: whether the tests pass today. No public CI runs them",
      "unchecked: the registration date of agent-zero.ai, the MCP registry, the Launcher, installer and A0 CLI repositories, and the site's docs pages other than secrets",
      "unchecked: where the Telegram, WhatsApp and email settings are encrypted, if anywhere. The source stores plugin settings as `config.json` and secrets as `secrets.env` under `/a0/usr`",
      "The GitHub API reports the licence as NOASSERTION because the file adds contact lines. Its text is the MIT licence",
      "The repository's last push was 11 October 2026, while main's last commit is 23 September, so current work sits on other branches",
      "Researched as a candidate for the personal assistants category and listed under agent harnesses, because its README calls it an agent framework and Linux workbench and its messaging channels, scheduler and memory are plugins."
    ],
    "weaknesses": [
      "No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow",
      "The web interface has no login until the owner sets a username, and the README command publishes port 80",
      "Five CVEs published between 17 March and 30 September 2026, none as a GitHub advisory, and no SECURITY.md or security.txt",
      "Infection Check, the prompt-injection audit before tool calls, ships turned off",
      "Empty allow-lists in the Telegram, WhatsApp and email integrations accept messages from anyone",
      "No public CI runs the 191 test files. The only workflows publish Docker images and close inactive issues"
    ],
    "agentNotes": [
      "Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none",
      "Fill `allowed_users`, `allowed_numbers` or `sender_whitelist` before enabling a channel. An empty list accepts every sender",
      "Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled",
      "Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal",
      "Call `POST /api_message` with the `X-API-KEY` header. The token changes when the UI login or password changes"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-12",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}