plan-in-files
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for task management and documentation. It does not initiate network requests, download external resources, or execute potentially dangerous commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input to generate task descriptions and constraints within a plan file. While this technically involves untrusted data entering the filesystem, the content is treated as documentation rather than executable code, posing no significant security risk.
- [COMMAND_EXECUTION]: The skill mentions using Git commands (like
git log,git diff) and user-defined verification commands. These are used strictly for verifying task progress within the developer's local environment and do not involve unsanitized remote input.
Audit Metadata