executing-plans
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to load, review, and execute instructions from an external plan file, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill reads external plan files in "Step 1: Load and Review Plan".
- Boundary markers: The skill instructs the agent to "Review critically" and "Raise concerns with your human partner" before starting, which serves as a manual checkpoint, but there are no technical delimiters or sanitization steps to isolate instructions from data within the plan file.
- Capability inventory: The skill is designed to "Follow each step exactly" and "Run verifications," implying it uses shell commands or other active tools to implement the plan's tasks.
- Sanitization: There is no mention of escaping, filtering, or validating the content of the plan file before the agent attempts to execute the steps contained within it.
Audit Metadata