routerbase-model-routing
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of high-level instructions and documentation guidelines for model selection and routing policies. It does not contain any scripts, executable commands, or network operations.
- [PROMPT_INJECTION]: The instructions follow standard behavioral guidelines and do not contain patterns designed to bypass safety filters, override system prompts, or extract internal instructions.
- [DATA_EXFILTRATION]: No sensitive file paths, credential markers, or data transfer commands were detected. The only external link is to the official RouterBase website.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any package installations or remote script execution. No dynamic code evaluation patterns are present.
- [COMMAND_EXECUTION]: There are no shell commands, system calls, or subprocess executions defined within the skill.
Audit Metadata