anygen-storybook

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls the AnyGen public OpenAPI (www.anygen.io) — see SKILL.md Phase 1/2 and scripts/anygen.py (prepare_task, create_task, poll_task, get_messages/poll_messages) — and requires the agent to read and act on untrusted service responses such as the prepare "reply"/"suggested_task_params" and task messages/outputs, which can materially influence subsequent tool use and actions.

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 OpenAPI (e.g., https://www.anygen.io/v1/openapi/tasks/prepare and other https://www.anygen.io endpoints) and consumes the returned "reply"/"suggested_task_params" (including prompts) which are then used directly to drive task creation and agent behavior, so external content from that URL can control prompts at runtime.