Wentor API

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires including a Wentor API token in the Authorization: Bearer header for requests, which forces the agent to place a secret value verbatim into generated requests/outputs.

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

• Third-party content exposure detected (high risk: 0.70). The skill's required wentor_qa and wentor_search endpoints fetch and return content (paper metadata and text) from Wentor's external index of academic/public papers, which the agent is expected to read and use to answer queries or drive follow-up actions (e.g., producing plots), exposing it to untrusted third-party content that could influence behavior.