review-and-recommend
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze potentially untrusted external data, such as git history, issue tracker content, and source code, creating an attack surface for indirect prompt injection.
- Ingestion points: Processes git logs, issues, and codebases (SKILL.md).
- Boundary markers: The instructions do not define delimiters or provide guidance to the agent for distinguishing between data and instructions within the analyzed sources.
- Capability inventory: The skill focuses on analysis and recommendation; the explicit instruction to stop and wait for a user choice before implementation serves as a primary security control against automated execution of injected instructions.
- Sanitization: No content sanitization or validation logic is specified for the data retrieved from external sources.
Audit Metadata