prp-wizard

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates a legitimate requirements engineering workflow (PRP) without malicious intent.
  • [COMMAND_EXECUTION]: The skill outlines a validation framework that utilizes standard build and test commands (e.g., npm run build, pytest, eslint). These are executed within the local project context for verification purposes.
  • [PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection as it processes user-provided feature requirements.
  • Ingestion points: User input for feature names, descriptions, and user stories gathered in Phase 1 (SKILL.md).
  • Boundary markers: Absent. The PRD and task templates do not use specific delimiters to isolate user-provided text.
  • Capability inventory: Execution of build/test commands and management of project tasks and documents via internal APIs (SKILL.md, Phases 5 & 7).
  • Sanitization: No explicit sanitization of user-provided content is performed prior to interpolation into documents or task descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 11:09 AM
Security Audit — agent-trust-hub — prp-wizard