prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a project management utility that facilitates the decomposition of requirements into actionable tasks. It operates on local markdown files and includes a mandatory human-in-the-loop step where the user must approve the task list before any files are written to the disk.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from a user-specified PRD file, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads the content of the PRD file provided by the user in Step 1.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its instructions and the content of the PRD.
- Capability inventory: The skill is capable of reading local files, listing directory contents, and writing new markdown files to the
issues/directory. - Sanitization: No sanitization or filtering of the PRD content is performed before analysis.
- Risk Assessment: This surface is considered low risk due to the limited capabilities of the skill and the requirement for user confirmation before the agent takes action based on the PRD analysis.
Audit Metadata