proj-analyze-req

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user requirements to generate formal documentation, which introduces a surface for indirect prompt injection attacks where malicious input could influence downstream agent actions.
  • Ingestion points: Untrusted user input is collected during the requirement understanding (Step 1) and clarification (Step 3) phases in SKILL.md.
  • Boundary markers: The skill partially mitigates this by requiring the agent to repeat its understanding to the user and request explicit confirmation (Step 5.1) before proceeding.
  • Capability inventory: The skill is capable of writing content to local files in the docs/task/ and docs/req/ directories (SKILL.md, Step 0 and Step 4).
  • Sanitization: There are no instructions for sanitizing or escaping user-provided text before it is interpolated into the markdown templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 10:08 AM
Security Audit — agent-trust-hub — proj-analyze-req