quick-ref
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strict file access constraints, specifically targeting only files within the
docs/onboarding/directory and limiting the agent to reading a maximum of 4 files before responding. - [SAFE]: No network operations (exfiltration), remote downloads, or external dependencies are present in the skill definition.
- [SAFE]: The skill does not contain any executable code or instructions for arbitrary command execution. It uses standard search tools (grep) within defined boundaries.
- [SAFE]: There are no signs of prompt injection, obfuscation, or persistence mechanisms. The metadata and instructions are consistent with the stated purpose of providing a quick reference for project structure.
Audit Metadata