route-work

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided evidence and task context to select a workflow and generate a kickoff message. Maliciously crafted input could lead to multi-step chain attacks where the generated kickoff contains instructions that subvert the behavior of the downstream workflow.
  • [NO_CODE]: No executable scripts or shell commands were found within the provided skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 09:11 PM
Security Audit — agent-trust-hub — route-work