security-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary task is analyzing untrusted code, which provides a surface for indirect prompt injection.
- Ingestion points: The skill analyzes external code files and diffs provided to the agent.
- Boundary markers: No explicit delimiters are used to separate skill instructions from the code content.
- Capability inventory: The skill only generates text reports and does not have access to dangerous capabilities like file writing or network access.
- Sanitization: Input content is not sanitized or filtered before processing.
Audit Metadata