azure-mgmt-apimanagement-py

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes examples that embed a secret literal (value="secret-key-value") and prints subscription.primary_key, which require the agent to include/expose secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly includes an "Import API from URL" workflow that ingests an OpenAPI document from an arbitrary public URL (e.g., ContentFormat.OPENAPI_LINK with value "https://petstore.swagger.io/v2/swagger.json"), so the agent would fetch and interpret untrusted third-party content which could alter API configuration/behavior.