social-media-management

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

• Third-party content exposure detected (high risk: 0.90). The "Reverse Engineering Viral Content" workflow explicitly directs the agent to "Find creators — 10–20 accounts" and "Collect data — 500+ posts for pattern analysis," which requires ingesting and analyzing public social-media/user-generated content (untrusted third-party sources) that can materially shape recommendations and next actions.