skills/garrytan/gbrain/draft-in-voice/Gen Agent Trust Hub

draft-in-voice

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the agent's internal environment using platform-specific gbrain tools for data retrieval and storage.
  • [SAFE]: No network activity, external exfiltration, or remote code execution patterns were identified. All data ingestion is focused on first-party context and user-provided samples.
  • [SAFE]: The skill incorporates strong security and quality controls, including a 'refuse-to-draft' policy for unvalidated or stale profiles and a mandatory human-in-the-loop validation process for profile creation.
  • [SAFE]: Command execution is limited to specific platform utilities (gbrain) with inputs handled safely (e.g., passing page content via stdin rather than command-line arguments).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 06:05 PM
Security Audit — agent-trust-hub — draft-in-voice