agent-routing
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content regarding model selection and cost-optimization strategies (cascading and loops).
- [EXTERNAL_DOWNLOADS]: The skill references a documentation URL (
https://platform.claude.com/docs/en/managed-agents/events-and-streaming#event-deltas) which is an official service domain and considered safe. - [COMMAND_EXECUTION]: The skill mentions operational commands for monitoring agent streams (e.g.,
GET /v1/sessions/...) and generic development tools (Python scorers), but does not execute arbitrary or dangerous code. It instructs the agent on how to use standard orchestration features available in its environment.
Audit Metadata