the-routing-engine

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill includes a dedicated security policy (references/agent-security.md) that explicitly instructs the agent to treat external content as data rather than instructions, mitigating prompt injection risks.
  • [SAFE]: The instructions contain clear guidelines against using protected personal attributes for scoring or routing, adhering to ethical AI principles.
  • [SAFE]: Data handling practices emphasize privacy, instructing the agent to redact secrets, avoid persisting raw personal data, and minimize file writes to the .agents/ directory.
  • [SAFE]: No suspicious remote code execution, external package dependencies, or unauthorized network operations were identified.
  • [SAFE]: The skill does not use obfuscation techniques; all instructions and references are in plain text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:03 PM