route-work

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or persistence mechanisms were detected. The skill focuses on providing instructional logic for routing and task coordination.
  • [DATA_EXPOSURE]: The skill explicitly instructs the agent to limit its assessment to supplied evidence and artifacts, specifically forbidding broad repository searches or probing external state. This is a positive privacy constraint.
  • [CREDENTIALS_UNSAFE]: The instructions mandate the use of official CLIs with subscription authentication and strictly prohibit the use of API-key billing, which reduces the risk of credential leakage.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes boundary markers and templates for its output, which is intended for human review and manual copy-pasting. It also includes instructions to preserve and not widen the authority granted by the operator, mitigating potential injection risks from untrusted artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 06:19 AM