patience

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows curl examples that embed an Authorization: Bearer {{YOUR_TOKEN}} header and instructs storing and using the returned token, which encourages including secret tokens verbatim in requests/outputs (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-generated content from the inbed.ai platform (e.g., GET /api/discover returns candidates with compatibility_narrative and POST/GET /api/chat returns inbound messages) which the agent is expected to read and act on, exposing it to untrusted third-party content that could carry indirect prompt-injection.