metal
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from arbitrary codebases, creating an indirect prompt injection surface.
- Ingestion points: Reads repository source code, documentation, and configuration files.
- Boundary markers: No explicit delimiters or instructions are used to separate analyzed data from the agent's instructions.
- Capability inventory: Utilizes Read, Grep, Glob, and Bash tools to examine repository contents.
- Sanitization: No evidence of validation or sanitization of the content extracted from external files is present.
Audit Metadata