product0-using-brief
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted product brief files, which creates an indirect prompt injection surface.
- Ingestion points: SKILL.md (Start, step 2) directs the agent to read the entire brief file into its context.
- Boundary markers: No specific delimiters are provided to isolate the brief's content from the agent's instructions.
- Capability inventory: The skill uses file read/write access to the project repository to inspect context and create decision request documentation.
- Sanitization: There is no evidence of input validation or sanitization for the content read from the brief files.
Audit Metadata