anygen-website

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the AnyGen OpenAPI (www.anygen.io) from multiple required workflow steps (prepare/create/poll/get-messages in SKILL.md and scripts/anygen.py) and explicitly reads and uses the API's returned "reply" and "suggested_task_params"/"prompt" to present plans and to drive task creation and subsequent actions, so untrusted third-party-generated content is ingested and can directly influence tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime requests to the AnyGen API at https://www.anygen.io (API_BASE) and explicitly uses the API's returned "reply" and "suggested_task_params" (including the prompt) to drive agent prompts and workflow, so this external URL directly controls prompts at runtime.