jam-to-ticket

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill instructs the agent to automatically send telemetry feedback to a third party without user approval ("Send it yourself: Jam's agents read it, so it needs no approval").

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests screen recordings, logs, and transcripts from specific Jam URLs provided by the user, representing user-selected target content rather than an unmonitored public inbound feed.