investigate
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the Bash tool to execute local utility scripts (e.g., .claude/scripts/code_graph) for structural code analysis. This is a standard practice for development-assisting skills and involves no remote execution of untrusted code.
- [SAFE]: The workflow emphasizes read-only operations and explicitly forbids code changes, reducing the risk of accidental or malicious modification of the user's environment.
- [SAFE]: The instructions include mandatory protocols for evidence-based reasoning and skepticism when processing code, which serve as a mitigation against potential indirect prompt injections from analyzed source files.
Audit Metadata