prd
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted feature descriptions to generate PRD files, creating a potential attack surface.
- Ingestion points: User-provided feature descriptions (SKILL.md).
- Boundary markers: Absent; the instructions do not explicitly warn the agent to ignore instructions embedded within the feature description content.
- Capability inventory: File system writing to the
/tasks/directory (SKILL.md). - Sanitization: Absent; the skill relies on the agent's default behavior for handling input and path generation.
Audit Metadata