plan-review
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 process and analyze implementation plans which may come from untrusted sources, potentially leading to indirect prompt injection.
- Ingestion points: The workflow requires reading external implementation plans and project-specific instructions (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined to separate the plans from the agent's system instructions.
- Capability inventory: The skill utilizes file-reading and analysis tools to verify paths, symbols, and dependencies mentioned in the plan.
- Sanitization: The instructions do not specify any validation or sanitization of the content within the implementation plans before analysis.
Audit Metadata