configuring-connections
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines configuration parameters for authenticating to a wide variety of external systems (NetSuite, Salesforce, AWS, databases, etc.) using established security protocols such as OAuth 2.0, JWT, and mTLS.
- [SAFE]: The instructions include a dedicated section on 'Credential Discipline', which mandates that the agent must never request, accept, or display real credentials in chat, and should instead use placeholders to protect sensitive user data.
- [SAFE]: All external domains and resource references (e.g., celigo.com, salesforce.com, amazonaws.com, googleapis.com) are either associated with the vendor or belong to well-known technology providers.
- [SAFE]: Example values for sensitive fields like API keys, tokens, and secrets are clearly non-functional placeholders (e.g., 'AKIAIOSFODNN7EXAMPLE', 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9').
- [SAFE]: The skill documents legitimate platform features such as debug logging and script-based routing with appropriate security context, noting that sensitive fields are masked in debug outputs.
Audit Metadata