codebase-explorer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [SAFE] (SAFE): No malicious patterns or security risks detected. The skill provides architectural guidance and suggests standard file exploration commands (ls, cat, grep) for a specific software project.
- [INDIRECT_PROMPT_INJECTION] (INFO): The skill identifies an attack surface for processing untrusted codebase content. 1. Ingestion points: Codebase files read via 'cat' and 'grep' commands. 2. Boundary markers: Absent in the provided instructions. 3. Capability inventory: Restricted to read-only display; no file-write, network operations, or arbitrary command execution detected. 4. Sanitization: Absent; the skill passes raw content to the agent context.
Audit Metadata