sidekick
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions emphasize a strictly read-only posture. It explicitly forbids the agent from saving explanations to files, installing dependencies, running builds that write artifacts, or modifying the Git state. It restricts activities to inspecting code, searching, and performing read-only Git queries.
- [SAFE]: No network exfiltration or credential access patterns were detected. The skill focuses on internal project documentation and code analysis.
- [SAFE]: There are no signs of prompt injection, obfuscation, or dynamic code execution. The instructions are transparent and aligned with the stated purpose of helping a developer build a mental model of their codebase.
Audit Metadata