{"id":"71e3ef55-a924-45d3-bb8b-a361bdfff485","slug":"clawhub-bartelmost-agentshield-audit","name":"Agentshield Audit","description":"Privacy-First security audit with 77 local tests (52 live + 25 static). Works with OpenClaw, Hermes Agent, n8n (auto-detected), LangChain, and any AI agent p...","canonicalUrl":"https://www.xpersona.co/agent/clawhub-bartelmost-agentshield-audit","sourceUrl":"https://clawhub.ai/bartelmost/agentshield-audit","homepage":"https://clawhub.ai/bartelmost/skills/agentshield-audit","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/bartelmost/skills/agentshield-audit"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"1.0.36","freshnessAt":"2026-10-09T11:05:19.686Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"1.0.36"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/bartelmost/skills/agentshield-audit","sourceUrl":"https://clawhub.ai/bartelmost/skills/agentshield-audit","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T11:05:19.686Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-bartelmost-agentshield-audit/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bartelmost-agentshield-audit/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T11:05:19.686Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"2.9K downloads","href":"https://clawhub.ai/bartelmost/agentshield-audit","sourceUrl":"https://clawhub.ai/bartelmost/agentshield-audit","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T11:05:19.686Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.0.36","href":"https://clawhub.ai/bartelmost/agentshield-audit","sourceUrl":"https://clawhub.ai/bartelmost/agentshield-audit","sourceType":"release","confidence":"medium","observedAt":"2026-06-18T08:26:21.093Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-bartelmost-agentshield-audit/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bartelmost-agentshield-audit/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["2.9K downloads","Trust evidence available"],"agentCard":{"name":"Agentshield Audit","description":"Privacy-First security audit with 77 local tests (52 live + 25 static). Works with OpenClaw, Hermes Agent, n8n (auto-detected), LangChain, and any AI agent p...","source":"CLAWHUB","sourceId":"clawhub:s1709g2t9ptwbe5z1grvhq0ak583gvmb:agentshield-audit","homepage":"https://clawhub.ai/bartelmost/skills/agentshield-audit","repository":"https://clawhub.ai/bartelmost/agentshield-audit","documentation":"https://www.xpersona.co/agent/clawhub-bartelmost-agentshield-audit","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"bash","snippet":"# Install via ClawHub\nclawhub install agentshield-audit\n\n# Run your first audit\npython scripts/initiate_audit.py --auto\n\nv1.0.3 | 2026-02-23T12:38:38.231Z | user\n\nAgentShield Audit v1.0.3\n\n- Added initial documentation: CHANGELOG.md, README.md, and clawhub.json files.\n- Updated installation and usage instructions for easier setup.\n- Expanded feature list, including rate limiting, secret leakage scanning, certificate verification, and public verification endpoints.\n- Documented audit and verification command examples.\n- Listed key API endpoints and requirements for integration.\n\nv1.0.2 | 2026-02-21T16:52:01.512Z | user\n\nv6.0.0 - Privacy-First Release\n\nSecurity Improvements:\n- Added explicit human-in-the-loop consent for all sensitive operations\n- Agent must ask permission before sending system prompts or code\n- API key configuration required (no blind connections)\n- Ed25519 private keys stay local, never transmitted\n- 30-day log retention only (auto-deleted)\n- Added self-hosted deployment option\n\nData Handling:\n- Granular consent for each security module\n- Local processing where possible\n- Encrypted transmission (TLS 1.3)\n- No permanent storage of sensitive data\n\nScope:\n- Instruction-only skill (no automatic installs)\n- Human controls all data sharing decisions\n- Optional certificate issuance\n\nv1.0.1 | 2026-02-21T15:37:22.662Z | user\n\nv6.0.0 - Major Release with Agent Audit System\n\nNew Features:\n- 5 modular security modules (Input Sanitizer, Output DLP, Tool Sandbox, EchoLeak, Supply Chain)\n- Agent Audit with Ed25519 cryptographic certificates\n- Enhanced Security Audit endpoint\n- Public certificate verification\n- Complete API documentation\n\nImprovements:\n- Frontend-compatible response formats\n- PDF report generation\n- Supply chain malware detection\n\nv1.0.0 | 2026-02-20T23:52:38.614Z | auto\n\nInitial release of AgentShield Audit Skill.\n\n- Enables users to initiate and manage AgentShield security audits for AI agents.\n- Supports key functions: security audit, cryptograp"},{"kind":"example","language":"text","snippet":"**What you get:**\n- ✅ Mutual verification (both agents are who they claim to be)\n- ✅ Shared session key (for encrypted communication)\n- ✅ Trust score boost (+5 for successful handshakes)\n- ✅ Public track record (handshake history)\n\n### 4. Public Trust Registry\n- **Searchable database** of all certified agents\n- **Reputation scores** based on audits, handshakes, and time\n- **Trust tiers:** UNVERIFIED → BASIC → VERIFIED → TRUSTED\n- **Revocation list (CRL)** - Compromised agents get flagged\n\n---\n\n## 🚀 Quick Start\n\n### Install"}]}}