secret-leak-detector
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files and git history data, making it susceptible to indirect prompt injection.
- Ingestion points: File contents and git logs accessed via the user-provided
directory_path. - Boundary markers: No delimiters or specific instructions are provided to ensure the agent disregards natural language instructions found within scanned files.
- Capability inventory: Performs file system reads and traverses git commit history.
- Sanitization: No input sanitization is mentioned to filter malicious instructions within source code or logs.
Audit Metadata