plan-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a common attack surface for indirect prompt injection by processing untrusted external data.
- Ingestion points: The skill is designed to read and analyze technical plans, proposals, or design documents provided by the user or found in the project (SKILL.md, Section 1).
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within the plans being reviewed.
- Capability inventory: While the skill is explicitly defined as read-only and does not modify code, it utilizes the
AskUserQuestiontool and has access to project detection patterns inreferences/project-detection.md. Malicious instructions in a plan could attempt to influence the agent's subsequent behavior or findings. - Sanitization: There is no evidence of input sanitization or escaping of the plan content before it is incorporated into the agent's reasoning context.
Audit Metadata