router
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill does not contain instructions designed to bypass safety filters or manipulate the agent's core behavior.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file access (e.g., SSH keys, env files) or hardcoded secrets were detected. Network activity is abstracted through local modules.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The code uses dynamic imports for local relative paths (../../../execution/smart-router), which is consistent with the project's internal structure. No remote script execution or dangerous eval() calls are present.
- [Indirect Prompt Injection] (LOW): 1. Ingestion points: User-supplied marketId and order details in the /router route command. 2. Boundary markers: None explicitly implemented in this CLI wrapper. 3. Capability inventory: Financial routing calculations and comparison logic; no file-writing or subprocess capabilities found in analyzed files. 4. Sanitization: Basic validation for numeric inputs (size); market identifiers are used as strings.
Audit Metadata