smart-routing
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- [General Security] (SAFE): The skill consists entirely of markdown instructions and a decision matrix for model routing. It does not perform any actions that interact with the file system, network, or external processes.
- [Prompt Injection] (SAFE): While the skill uses strong language like 'IMPORTANT' and 'DO NOT', these are functional instructions meant to improve the quality of the agent's output by selecting better models, rather than attempts to bypass safety filters or ignore system prompts.
- [Data Exposure & Exfiltration] (SAFE): No credentials, sensitive file paths, or network exfiltration patterns were detected.
- [Remote Code Execution] (SAFE): The skill does not download or execute any external scripts or packages.
- [Indirect Prompt Injection] (SAFE): The skill defines how to respond to certain keywords in user queries (e.g., 'fix', 'where is'), but it does not ingest untrusted data from external sources or provide a mechanism for such data to influence the agent's core safety logic.
Audit Metadata