aw-create-plan
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill's primary function is creating implementation plans for future sessions, which constitutes an indirect prompt injection surface.
- Ingestion points: The generated
plan.mdfile in the.agent/directory. - Boundary markers: The plan template lacks explicit delimiters to distinguish between system-provided instructions and user-controlled requirement descriptions.
- Capability inventory: Subsequent sessions reading the plan typically possess file-writing and command-execution capabilities to implement the plan.
- Sanitization: Content from the current conversation is interpolated directly into the markdown plan without escaping or validation.
Audit Metadata