code-review
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted source code, creating a surface for potential indirect prompt injection.
- Ingestion points: The skill ingests repository content and code changes as specified in the SKILL.md invocation and scope sections.
- Boundary markers: No explicit instructions are provided to use delimiters or boundary markers when processing external code.
- Capability inventory: The skill utilizes file reading and navigation capabilities, but explicitly restricts workers to read-only operations to prevent unauthorized modifications.
- Sanitization: There is no evidence of sanitization or filtering of the ingested code before it is processed by the agent.
Audit Metadata