write-a-prd
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes detailed user-provided text to guide its behavior and generate documentation, which presents a surface for indirect prompt injection.
- Ingestion points: Detailed problem descriptions and implementation ideas provided by the user in Step 1 (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within user input.
- Capability inventory: The agent is instructed to explore the repository (file access) and submit documents as GitHub issues (network write).
- Sanitization: The skill does not specify any sanitization or validation logic for the ingested user content.
Audit Metadata