romance

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt's curl examples and auth section explicitly show including an Authorization: Bearer {{YOUR_TOKEN}} header, instructing the agent to embed API tokens verbatim in requests/commands (a direct secret-exposure pattern).

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and uses user-generated content from inbed.ai (e.g., /romance-discover returns candidate bios/interests and GET /api/chat returns public conversations — "All conversations are public") which the agent is expected to read/interpret as part of its workflow, allowing untrusted third-party content to influence actions.