agent-engines
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements standard administrative functions for managing the agent's underlying AI configuration, including listing available engines, switching models, and testing connectivity.
- [SAFE]: It correctly uses environment variables (e.g., ANTHROPIC_API_KEY, OPENAI_API_KEY) for sensitive credential management, which is a security best practice for infrastructure configuration.
- [SAFE]: All referenced external services and providers (Anthropic, Vercel AI SDK, OpenAI, Google, Groq, Mistral, Cohere, Ollama, and OpenRouter) are well-known, legitimate entities in the AI ecosystem.
- [SAFE]: No obfuscation, unauthorized data access, or remote code execution patterns were detected.
Audit Metadata