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