prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows its stated purpose of assisting with project management tasks. It uses standard developer tools (
ghCLI) to read and write GitHub issues based on user-provided identifiers. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests data from external GitHub issues which could contain untrusted instructions.
- Ingestion points: The skill fetches PRD content from GitHub via the
gh issue viewcommand. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between PRD data and potential embedded instructions.
- Capability inventory: The skill utilizes
gh issue viewfor reading andgh issue createfor writing to the repository. - Sanitization: There is no specific validation or sanitization of the content retrieved from the PRD before it is processed by the agent.
Audit Metadata