executing-plans

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for a standard task management workflow. It utilizes common developer tools such as pytest, vitest, and the just command runner for routine testing and linting tasks.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external plan documents, which constitutes a surface for indirect prompt injection. This behavior is expected given the skill's role in executing arbitrary development plans.
  • Ingestion points: Plan documents and task lists found in files matching the file_patterns defined in SKILL.md (e.g., **/TODO.md, **/planning/**).
  • Boundary markers: None identified in the skill instructions to distinguish between plan data and executable instructions.
  • Capability inventory: The skill is capable of executing shell commands for testing, linting, and visual verification as described in SKILL.md.
  • Sanitization: No evidence of input sanitization or validation for the plan content was found in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:47 PM
Security Audit — agent-trust-hub — executing-plans