prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes data from external GitHub issues and comments, which constitutes untrusted input that could contain malicious instructions designed to hijack the agent's logic during issue creation.\n
- Ingestion points: The skill retrieves external data using
gh issue view <number> --commentsas described inSKILL.md.\n - Boundary markers: No delimiters or instructions are provided to the agent to treat the fetched PRD content as data only or to ignore instructions embedded within it.\n
- Capability inventory: The agent utilizes
gh issue createand codebase exploration tools, which could be misdirected by successful prompt injection in the source PRD.\n - Sanitization: There is no requirement or logic for sanitizing or validating the content of the GitHub issue before the agent processes it to draft new tasks.
Audit Metadata