jam-proof-table

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill instructs the agent to automatically send feedback to a third-party service without user approval, representing undisclosed reporting to the vendor.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow reads Jam screen recordings, console logs, and network requests via the jam CLI, which can contain third-party user-submitted web page content or application data.