readme
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data from a user's codebase to generate documentation.
- Ingestion points: The skill reads various project files including
Gemfile,package.json,.env.example, anddb/schema.rb(references/detailed-guide.md). - Boundary markers: The instructions include explicit mandates to verify project facts against source code and forbid inventing authentication helpers or deployment claims.
- Capability inventory: The agent is authorized to read project files and write to a
README.mdfile; however, it is explicitly denied authorization for command execution, dependency installation, or database operations. - Sanitization: The skill contains strict guidelines never to copy production database URLs, master keys, or raw secrets into the documentation.
Audit Metadata