{"skill":{"slug":"edvisage-trust-checker","displayName":"Edvisage Trust Checker","summary":"A protocol-layer trust verification skill for AI agents. Before you read, install, or transact — check first. Protects against prompt injection, malicious sk...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":90,"installsAllTime":0,"installsCurrent":0,"stars":1,"versions":1},"createdAt":1775030343509,"updatedAt":1775031113814},"latestVersion":{"version":"1.0.0","createdAt":1775030343509,"changelog":"Initial release of trust-checker, a protocol-layer trust verification skill for AI agents:\n\n- Introduces a structured verification process to protect agents against prompt injection, malicious skills, and unverified agents.\n- Provides a four-step trust protocol for safe interactions with unknown content, skill installation, and agent transactions.\n- Protocol emphasizes manual verification of source, intent, content integrity, and owner authorization before action.\n- Includes a specific checklist for secure skill installation, including repository checks, VirusTotal scans, permissions review, and author verification.\n- No automated scanning; this skill establishes protocols and habits to be followed before trusting non-owner-originated inputs.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"edvisage","userId":"s1708f8ytc8gb38s8hkw378pw983n3sj","displayName":"Edvisage Global","image":"https://avatars.githubusercontent.com/u/268633876?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.prompt_injection_instructions"],"summary":"Detected: suspicious.prompt_injection_instructions","engineVersion":"v2.2.0","updatedAt":1775031113814}}