litellm-guardrails-safety
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to improve the security posture of LLM integrations by teaching the agent how to configure LiteLLM guardrails, PII masking, and tool permissions.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation from LiteLLM (docs.litellm.ai), which is a well-known service in the LLM ecosystem. These references are used for informational purposes to guide the configuration of safety features.
- [PROMPT_INJECTION]: The skill includes instructions specifically aimed at mitigating prompt injection risks through the implementation of guardrails and threat modeling.
- [DATA_EXFILTRATION]: The instructions explicitly forbid logging secrets or unmasked PII in custom hooks, demonstrating a clear focus on preventing data exposure.
Audit Metadata