Missing User Warnings
Medium
- Confidence
- 93% confidence
- Finding
- The skill explicitly instructs agents to POST a free-form natural-language intent string to an external endpoint, but it does not warn that this text may contain sensitive data such as user goals, internal context, identifiers, or regulated information. Because the router is meant to classify arbitrary agent needs, users or upstream agents may overshare secrets or confidential business context, creating an avoidable data disclosure risk.
