executing-plans
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and execute steps from external 'plan' files, creating a vulnerability surface for indirect prompt injection. 1. Ingestion points: Step 1 (Load and Review Plan) explicitly reads an external file. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded malicious content in the plan files. 3. Capability inventory: The skill directs the agent to execute implementation tasks, run verifications, and call a sub-skill ('finishing-a-development-branch'). 4. Sanitization: Mitigation relies on the agent's 'critical review' and a human-in-the-loop checkpoint system.
- [No Code] (SAFE): No executable code scripts (Python, JavaScript, etc.) or package dependencies are included in the skill definition.
Audit Metadata