breakdown-feature-prd

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs to generate content, which creates a surface for potential indirect prompt injection.
  • Ingestion points: Input is gathered through fields like 'Epic', 'Feature Idea', and 'Target Users' in the Context Template section of SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the template to isolate untrusted input.
  • Capability inventory: The instructions include the capability to write the resulting PRD to the local filesystem at a specified path in the /docs/ directory.
  • Sanitization: No input validation, escaping, or sanitization mechanisms are defined in the instructions to handle external content safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:49 AM
Security Audit — agent-trust-hub — breakdown-feature-prd