write-a-prd
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the repository to inform the PRD creation, which introduces an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to explore the repository in Step 3 to verify user assertions and understand the current codebase.
- Boundary markers: No explicit delimiters or instructions are present to ensure the agent ignores or isolates instructions found within the repository files.
- Capability inventory: The skill possesses the capability to read local files and submit data to external services (GitHub issues).
- Sanitization: The instructions do not define any sanitization or filtering logic for the data ingested from the repository.
- Mitigation: A mandatory human-in-the-loop step (Step 6) requires user review and explicit approval of the draft PRD before it is submitted as a GitHub issue, reducing the risk of automated malicious actions.
Audit Metadata