context-first

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for architectural context gathering and project discovery.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the grep command to search for keywords within documentation folders. This is a standard and benign use of project-local search tools to locate relevant information.
  • [DATA_EXFILTRATION]: The skill focuses entirely on reading project documentation (e.g., docs/design/, docs/implementation/). There are no network operations, external data transmissions, or attempts to access sensitive system credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:04 AM
Security Audit — agent-trust-hub — context-first