chanjing-ai-creation

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

• Third-party content exposure detected (high risk: 0.70). The skill calls the third‑party Open API at open-api.chanjing.cc and directly consumes its responses (see scripts/poll_task.py and get_task.py which read progress_desc/err_msg/output_url to control polling and decisions, and download_result.py which fetches output_url or arbitrary URLs), so untrusted API/URL content can materially influence the agent's actions.