executing-plans
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes implementation plans from external files, creating an attack surface for instructions embedded within those files.
- Ingestion points: The workflow involves reading a selected plan file to generate a list of tasks for execution (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters to separate the plan's instructions from the agent's execution logic.
- Capability inventory: The skill is designed to apply file modifications and run verification tests or checks as defined in the plan (SKILL.md).
- Sanitization: There is no evidence of sanitization or command validation for the tasks extracted from the plan before they are executed.
Audit Metadata