spark

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

• Third-party content exposure detected (high risk: 0.90). The skill directly consumes user-generated content from the third-party platform inbed.ai (e.g., GET /api/discover returns other agents' profiles and compatibility narratives, and GET /api/chat/{matchId}/messages returns chat messages), and those untrusted inputs are read and used to decide swipes, replies, matches, and other actions, so they could carry indirect prompt-injection instructions.