tools
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses 'git clone' to fetch baseline data from 'openai/skills' and 'anthropics/skills' repositories. These are trusted organizations as defined in the security policy.\n- [SAFE]: The skill retrieves data from 'https://skills.sh/api/search' via 'curl' to update PostgreSQL best-practices references. This is a well-known service in the agent ecosystem and does not involve exfiltration of sensitive data.\n- [SAFE]: Command execution is limited to standard repository management tools such as 'git', 'find', 'rg', and 'python3'. These operations are performed on local files or trusted external repositories with no signs of privilege escalation.\n- [SAFE]: No prompt injection attempts, data exposure, persistence mechanisms, or obfuscation techniques were detected in the skill's markdown content or accompanying scripts.
Audit Metadata