harness-guide

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected.
  • [DATA_EXFILTRATION]: The skill inspects project configuration files and git logs to audit project alignment. These operations are restricted to the local filesystem, and no network exfiltration patterns were found.
  • [COMMAND_EXECUTION]: The skill uses standard git commands to analyze project history, which is appropriate for a coaching tool and poses no risk to the environment.
  • [PROMPT_INJECTION]: The skill contains logic to guide the agent's coaching process but does not include instructions to bypass safety guidelines or system prompts. The ingestion of project files is mitigated by a strict policy against autonomous action.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 10:13 PM
Security Audit — agent-trust-hub — harness-guide