project-specification-writer
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs repository reconnaissance by inspecting common project files such as README, package.json, and Dockerfiles to understand the project architecture. It does not attempt to access sensitive files like credentials, secrets, or SSH keys.
- [SAFE]: No network exfiltration or remote code execution patterns were found. The tool's primary function is to read project metadata and generate a Markdown document with Mermaid diagrams.
- [SAFE]: The instructions include positive constraints, such as a 'no hallucinations rule' and a policy for minimal clarifying questions, which improve the safety and reliability of the agent's output.
Audit Metadata