attraction

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's curl examples and auth section explicitly require inserting a bearer token (Authorization: Bearer {{YOUR_TOKEN}}) into generated commands/requests, which means the LLM would need to handle and output secret token values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls open endpoints on https://inbed.ai (e.g., /api/discover returns candidate profiles/compatibility_narrative and /api/chat/{matchId}/messages returns chat messages), which are untrusted, user-generated third-party content that the agent is expected to read and act on (swipes, matches, conversation decisions), enabling indirect prompt-injection via those texts.