prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
ghcommand-line tool to fetch issue details and create new tickets on GitHub. - [DATA_EXFILTRATION]: The skill reads content from a PRD on GitHub and transmits transformed data back to GitHub to create new issues. This is consistent with the skill's purpose.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when processing external PRD content.
- Ingestion points: Untrusted PRD content is ingested via
gh issue viewin SKILL.md. - Boundary markers: No explicit delimiters or instructions are used to isolate the PRD data from the agent's operational logic.
- Capability inventory: The agent can perform write operations to the repository using
gh issue create. - Sanitization: No explicit sanitization is performed on the ingested text.
- Sanitization: The risk is primarily mitigated by a mandatory human review step ('Quiz the user') which occurs before any issues are created.
Audit Metadata