executing-plans

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard development workflow for tracking tasks and verifying progress with local tools.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as its primary purpose is to ingest and execute instructions from a previously generated plan.
  • Ingestion points: Plan output in the thread context (SKILL.md).
  • Boundary markers: None explicitly mentioned in the skill instructions.
  • Capability inventory: Local shell command execution for testing and linting purposes (SKILL.md).
  • Sanitization: Not present; the skill assumes the validity of the input plan data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:22 PM
Security Audit — agent-trust-hub — executing-plans