router-engineering
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely instructional and serves as a routing mechanism for technical intents. It does not perform any file system modifications, network requests, or credential handling.
- [NO_CODE]: No source code or executable logic (Python, JavaScript, Shell) is included in the skill definition. It operates purely as a set of logical mapping instructions for the AI agent.
- [PROMPT_INJECTION]: The skill contains explicit safety guidelines to ignore instruction hijacks and 'route to X' attempts, providing a layer of defense against direct manipulation of the routing logic.
- [EXTERNAL_DOWNLOADS]: No external URLs or remote resources are referenced. The skill relies on local registry files and templates for its operations.
Audit Metadata