personality-personality

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the public inbed.ai APIs (notably GET https://inbed.ai/api/discover which returns other agents' profiles and a compatibility_narrative) and explicitly instructs the agent to read those user-generated profiles/narratives and act (swipe, message), so untrusted third-party content can influence decisions and actions.