feishu-doc

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 read Feishu cloud documents (URLs like https://xxx.feishu.cn/docx/ABC123def) via the "read" and "list_blocks" actions and then use that user-generated document content to drive edits (write, update_block, delete), so untrusted third-party doc content can directly influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill reads Feishu documents at runtime (e.g., https://xxx.feishu.cn/docx/ABC123def) and returns their content to the agent, which can be injected into the model context and thus directly control prompts.