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
Risk Level
SAFE
Analyzed
Jul 13, 2026, 01:46 PM
Security Audit — agent-trust-hub — product0-using-brief