dingtalk-docs-reader

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires a full browser Cookie string and X-XSRF-TOKEN (copied from DevTools) to be supplied and used in API requests, which forces the agent to handle and potentially embed those secret values verbatim in commands or requests.

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

• Third-party content exposure detected (high risk: 0.80). The skill programmatically fetches and parses user-generated documents from the public DingTalk/Alidocs site (e.g., API endpoints under https://alidocs.dingtalk.com such as /api/document/data, /box/api/v2/dentry/list and the space HTML page parsed in get_root_dentry_uuid), ingests their content via get_document_data/export_to_pdf/extract_text_from_alidocs, and therefore untrusted third‑party content can be read and influence the agent's outputs or subsequent actions.