yuque

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated Yuque content from the public Yuque OpenAPI (base URL https://www.yuque.com) — e.g., SKILL.md's "Read Workspace State" and references/doc.md/OpenAPI YAML show GET endpoints for docs, TOC, and search that the agent must ingest and which can materially change subsequent tool actions (creates/updates/moves), enabling indirect prompt injection.