project-requirements

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection when it extracts requirements from user-provided text.\n
  • Ingestion points: User-pasted requirements in the context of the /req spec or /req stories commands.\n
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within the user's requirements data.\n
  • Capability inventory: The skill is restricted to reading its own reference templates and writing Markdown files to a docs/ directory. It has no access to shell execution, network requests, or sensitive system files.\n
  • Sanitization: There are no mechanisms described for sanitizing or filtering input before it is structured into the final documents.\n- [NO_CODE]: The skill is comprised solely of Markdown files and configuration metadata, containing no Python scripts, Node.js packages, or binary executables.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:55 PM
Security Audit — agent-trust-hub — project-requirements