model-routing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified during the analysis of the instruction set.
- [EXTERNAL_DOWNLOADS]: The skill references technical documentation and prompting guides from several established technology providers and AI research organizations, including OpenAI, Google, Midjourney, ByteDance, and xAI. These references are used to provide authoritative model guidance.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for processing user generation requests to select models.
- Ingestion points: Processes user input to classify requests by kind, operation, priority, and structure (SKILL.md).
- Boundary markers: No specific technical delimiters are implemented to separate user data from internal instructions.
- Capability inventory: The skill is designed for informational routing and prompt construction; it does not include tools for file modification, network communication, or code execution.
- Sanitization: No input validation or content filtering mechanisms are defined.
Audit Metadata