executing-plans

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and execute instructions from external plan files, which presents an indirect prompt injection surface.
  • Ingestion points: The agent is instructed to read a plan file in Step 1.
  • Boundary markers: No specific delimiters for untrusted content are defined, though the instructions mandate a critical review process.
  • Capability inventory: Implementation involves code changes, running verifications/tests, and git operations via integrated sub-skills such as using-git-worktrees and finishing-a-development-branch.
  • Sanitization: The skill lacks automated sanitization of the plan content, relying on the agent's evaluation and scheduled checkpoints for human feedback to mitigate risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 04:50 AM