executing-plans
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes instructions from an external implementation plan file, which creates an indirect prompt injection surface.
- Ingestion points: Plan files are loaded and read during the 'Review Plan' step.
- Boundary markers: The skill lacks explicit markers to isolate plan content or instructions to ignore embedded malicious prompts; it explicitly directs the agent to 'Follow each step exactly'.
- Capability inventory: The skill possesses the capability to execute tasks and run verifications based on the contents of the plan.
- Sanitization: No sanitization or validation of the plan content is performed before the execution phase.
Audit Metadata