write-a-prd

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are purely functional and intended for documentation generation. No malicious code, obfuscation, or unauthorized data access patterns were detected.
  • [PROMPT_INJECTION]: The skill incorporates information from the repository's codebase to generate the PRD. While this creates an ingestion point for external data, it is a primary function of the skill and no malicious intent was observed.
  • Ingestion points: Local repository files (Step 2 in SKILL.md).
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Agent-provided file system research tools.
  • Sanitization: No explicit sanitization or filtering of codebase content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:15 AM
Security Audit — agent-trust-hub — write-a-prd