plugin-authoring
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious behaviors, prompt injections, or obfuscation patterns were detected. The skill is purely educational and procedural.
- COMMAND_EXECUTION (SAFE): The skill references standard development commands (such as chmod +x and /plugin-development:*), which are necessary for the documented plugin lifecycle and do not pose a security threat in this context.
- EXTERNAL_DOWNLOADS (LOW): The skill contains links to official Anthropic documentation. These are trusted sources according to the [TRUST-SCOPE-RULE], resulting in a LOW severity for the reference itself without impacting the overall SAFE verdict.
Audit Metadata