anygen-doc

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime calls to the AnyGen API (https://www.anygen.io) and uses the API's responses (e.g., suggested_task_params from /v1/openapi/tasks/prepare) to construct and control prompts and task creation, so remote content directly influences agent instructions and is a required dependency.