write-a-prd
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from the repository during codebase exploration.
- Ingestion points: Repository files accessed during the 'Explore the repo' step in SKILL.md.
- Boundary markers: No delimiters or instructions to ignore embedded commands within the repository files are provided.
- Capability inventory: The skill has the capability to read repository files and write to GitHub issues, which could allow malicious instructions in the codebase to influence the resulting PRD or issue.
- Sanitization: The instructions do not specify any validation or sanitization for the data retrieved from the codebase before it is used in the PRD template.
Audit Metadata