close-spec
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs routine file management and documentation tasks using standard tools like
git mv. It lacks any indicators of malicious intent, such as obfuscation, credential theft, or unauthorized network activity. - [INDIRECT_PROMPT_INJECTION]: The skill processes repository content (specs and source code) to generate documentation, which is a common pattern for AI-assisted development tools. While this theoretically allows the agent to process data containing instructions, the risk is mitigated by the skill's specific purpose of summarizing verified code and the requirement for human-verified implementation results (green tests/screenshots).
Audit Metadata