webhook-http-request

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's schema and examples require supplying sensitive values (auth_token, auth_password, auth_header_value, etc.) directly as parameters and show them verbatim in calls, which forces the LLM to handle and emit secrets in tool-invocation payloads.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is to send an HTTP request to a user-specified url and then ingest the HTTP response body (e.g., response_mode: "auto"/"text"/"json"), which can include outsider-authored free text from arbitrary public web content fetched at runtime.