semgrep
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code from a repository, which is untrusted data.
- Ingestion points: Source code files within the repository are scanned and processed.
- Boundary markers: The instructions do not define specific delimiters or isolation techniques to prevent the agent from following instructions potentially embedded within the source code files.
- Capability inventory: The skill utilizes Semgrep for pattern matching and references a verification tool via
/verify-security-finding. - Sanitization: No sanitization, escaping, or filtering of the code content is specified before the agent evaluates the findings.
Audit Metadata