configuring-guardrails
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines configuration schemas and documentation for "Guardrail" resources, which are specifically designed to implement safety and compliance checks (such as PII masking and content moderation) in data integrations.- [SAFE]: All referenced tools, such as the Celigo CLI, and infrastructure domains align with the author's identity and represent standard vendor-provided functionality.- [SAFE]: The AI agent configurations included in the schemas utilize industry-standard practices, such as structured JSON output, system prompt separation, and managed credentials, which enhance the security posture of the AI interactions.- [SAFE]: Capabilities for external data retrieval (web search, URL context) are documented as optional features for legitimate business use cases and are governed by the platform's security framework.
Audit Metadata