func

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly instructs the agent to fetch data from external sources ("帮用户获取数据并保存为 CSV" and "用 curl 下载、从 API 获取等" in the Behavior rules / Step 1), so it will ingest arbitrary public third‑party content (CSV/web downloads) as part of its processing pipeline, exposing it to untrusted input that can influence outputs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill embeds and relies on a remote script loaded at runtime (https://cdnjs.cloudflare.com/ajax/libs/echarts/5.4.3/echarts.min.js) which executes third‑party JavaScript in the renderer, so it fetches and runs external code required for the skill to display charts.