{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agent-audit-trail",
    "name": "Agent Audit Trail",
    "source": "tencent",
    "type": "skill",
    "category": "金融交易",
    "sourceUrl": "https://clawhub.ai/roosch269/agent-audit-trail",
    "canonicalUrl": "https://clawhub.ai/roosch269/agent-audit-trail",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agent-audit-trail",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-audit-trail",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "examples/basic-usage.sh",
      "examples/eu-ai-act-compliance.sh",
      "scripts/auditlog.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "agent-audit-trail",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-26T01:45:40.451Z",
      "expiresAt": "2026-05-03T01:45:40.451Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-audit-trail",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-audit-trail",
        "contentDisposition": "attachment; filename=\"agent-audit-trail-2.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "agent-audit-trail"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/agent-audit-trail"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/agent-audit-trail",
    "agentPageUrl": "https://openagent3.xyz/skills/agent-audit-trail/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-audit-trail/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-audit-trail/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Agent Audit Trail Skill",
        "body": "Tamper-evident, hash-chained audit logging for AI agents. EU AI Act compliant."
      },
      {
        "title": "Why",
        "body": "AI agents act on your behalf. From 2 August 2026, the EU AI Act requires automatic logging, tamper-evident records, and human oversight capability for AI systems. This skill provides all three with zero dependencies."
      },
      {
        "title": "1. Add to your agent's workspace",
        "body": "cp scripts/auditlog.py /path/to/your/workspace/scripts/\nchmod +x /path/to/your/workspace/scripts/auditlog.py"
      },
      {
        "title": "2. Log an action",
        "body": "./scripts/auditlog.py append \\\n  --kind \"file-write\" \\\n  --summary \"Created config.yaml\" \\\n  --target \"config.yaml\" \\\n  --domain \"personal\""
      },
      {
        "title": "3. Verify integrity",
        "body": "./scripts/auditlog.py verify\n# Output: OK (N entries verified)"
      },
      {
        "title": "Compliance Mapping",
        "body": "EU AI Act ArticleRequirementHow This Skill HelpsArt. 12 Record-KeepingAutomatic event loggingEvery action logged with timestamp, actor, domain, targetArt. 12 IntegrityTamper-evident recordsSHA-256 hash chaining — modification breaks the chainArt. 14 Human OversightHuman approval linkage--gate flag links actions to human approval referencesArt. 50 TransparencyAuditable recordsHuman-readable NDJSON, one-command verificationArt. 12 TraceabilityChronological orderingMonotonic ord tokens"
      },
      {
        "title": "Event Kinds",
        "body": "Use these standardised event types for consistent audit trails:\n\nKindWhen to Usefile-writeAgent creates or modifies filesexecAgent runs a commandapi-callExternal API interactiondecisionAI makes or recommends a decisioncredential-accessSecrets or credentials accessedexternal-writeAgent writes to external systemshuman-overrideHuman overrides an AI decisiondisclosureAI identity disclosed to user"
      },
      {
        "title": "Full Documentation",
        "body": "See README.md for complete usage, integration examples, security model, and EU AI Act compliance guide."
      },
      {
        "title": "Log Format",
        "body": "{\n  \"ts\": \"2026-02-24T07:15:00+00:00\",\n  \"kind\": \"exec\",\n  \"actor\": \"atlas\",\n  \"domain\": \"ops\",\n  \"plane\": \"action\",\n  \"target\": \"pg_dump production\",\n  \"summary\": \"Ran database backup\",\n  \"gate\": \"approval-123\",\n  \"ord\": 42,\n  \"chain\": {\"prev\": \"abc...\", \"hash\": \"def...\", \"algo\": \"sha256(prev\\\\nline_c14n)\"}\n}"
      },
      {
        "title": "OpenClaw Integration",
        "body": "Add to HEARTBEAT.md:\n\n## Audit integrity check\n- Run: `./scripts/auditlog.py verify`\n  - If fails: alert with line number + hash mismatch\n  - If OK: silent"
      },
      {
        "title": "Requirements",
        "body": "Python 3.9+ (zero external dependencies)\nMIT License\n\nBuilt with 🔐 by Roosch and Atlas"
      }
    ],
    "body": "Agent Audit Trail Skill\n\nTamper-evident, hash-chained audit logging for AI agents. EU AI Act compliant.\n\nWhy\n\nAI agents act on your behalf. From 2 August 2026, the EU AI Act requires automatic logging, tamper-evident records, and human oversight capability for AI systems. This skill provides all three with zero dependencies.\n\nQuick Start\n1. Add to your agent's workspace\ncp scripts/auditlog.py /path/to/your/workspace/scripts/\nchmod +x /path/to/your/workspace/scripts/auditlog.py\n\n2. Log an action\n./scripts/auditlog.py append \\\n  --kind \"file-write\" \\\n  --summary \"Created config.yaml\" \\\n  --target \"config.yaml\" \\\n  --domain \"personal\"\n\n3. Verify integrity\n./scripts/auditlog.py verify\n# Output: OK (N entries verified)\n\nCompliance Mapping\nEU AI Act Article\tRequirement\tHow This Skill Helps\nArt. 12 Record-Keeping\tAutomatic event logging\tEvery action logged with timestamp, actor, domain, target\nArt. 12 Integrity\tTamper-evident records\tSHA-256 hash chaining — modification breaks the chain\nArt. 14 Human Oversight\tHuman approval linkage\t--gate flag links actions to human approval references\nArt. 50 Transparency\tAuditable records\tHuman-readable NDJSON, one-command verification\nArt. 12 Traceability\tChronological ordering\tMonotonic ord tokens\nEvent Kinds\n\nUse these standardised event types for consistent audit trails:\n\nKind\tWhen to Use\nfile-write\tAgent creates or modifies files\nexec\tAgent runs a command\napi-call\tExternal API interaction\ndecision\tAI makes or recommends a decision\ncredential-access\tSecrets or credentials accessed\nexternal-write\tAgent writes to external systems\nhuman-override\tHuman overrides an AI decision\ndisclosure\tAI identity disclosed to user\nFull Documentation\n\nSee README.md for complete usage, integration examples, security model, and EU AI Act compliance guide.\n\nLog Format\n{\n  \"ts\": \"2026-02-24T07:15:00+00:00\",\n  \"kind\": \"exec\",\n  \"actor\": \"atlas\",\n  \"domain\": \"ops\",\n  \"plane\": \"action\",\n  \"target\": \"pg_dump production\",\n  \"summary\": \"Ran database backup\",\n  \"gate\": \"approval-123\",\n  \"ord\": 42,\n  \"chain\": {\"prev\": \"abc...\", \"hash\": \"def...\", \"algo\": \"sha256(prev\\\\nline_c14n)\"}\n}\n\nOpenClaw Integration\n\nAdd to HEARTBEAT.md:\n\n## Audit integrity check\n- Run: `./scripts/auditlog.py verify`\n  - If fails: alert with line number + hash mismatch\n  - If OK: silent\n\nRequirements\nPython 3.9+ (zero external dependencies)\nMIT License\n\nBuilt with 🔐 by Roosch and Atlas"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/roosch269/agent-audit-trail",
    "publisherUrl": "https://clawhub.ai/roosch269/agent-audit-trail",
    "owner": "roosch269",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agent-audit-trail",
    "downloadUrl": "https://openagent3.xyz/downloads/agent-audit-trail",
    "agentUrl": "https://openagent3.xyz/skills/agent-audit-trail/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-audit-trail/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-audit-trail/agent.md"
  }
}