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
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:08 AM
Security Audit — agent-trust-hub — quick-ref