dingtalk-skill-creator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse third‑party content—e.g., "访问 https://open.dingtalk.com/document/" and to make live requests to https://api.dingtalk.com (inspecting JSON responses and error messages) — and those external docs/responses are read and used to determine field names, permissions, test flow, and next actions.