agents-router

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions to bypass safety or override agent behavior were detected.- [Data Exposure & Exfiltration] (SAFE): No sensitive data access or network exfiltration patterns were found.- [Remote Code Execution] (SAFE): No downloads or execution of external code are present.- [Indirect Prompt Injection] (SAFE): The skill is purely informational and lacks executable capabilities. Ingestion points: Task descriptions are referenced as inputs for routing logic. Boundary markers: Not applicable for this documentation. Capability inventory: No execution, network, or file-system capabilities are present in the skill files. Sanitization: Not applicable for non-executable content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM