gohighlevel
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust safety model for CRM operations. It explicitly instructs the agent to 'Show the exact location, object, current value, proposed value, risk, and rollback before acting' and to 'Obtain approval, apply once, then read back.' These are best practices for AI-driven data management.
- [SAFE]: The instructions include measures to prevent data integrity issues, such as resolving existing identifiers before creating new records to avoid duplicates.
- [SAFE]: The skill uses a defined connection protocol (MCP) and handles authentication through a dedicated platform (NotFair), minimizing the risk of hardcoded credentials within the skill itself.
- [SAFE]: The evaluation cases (evals.json) reinforce the safety constraints, ensuring that the agent does not mutate data during read operations and does not perform automated retries on failed writes without user oversight.
Audit Metadata