feishu-docs

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly reads and ingests user-generated Feishu/Lark documents and wiki content (e.g., via "feishu-docs read <url|token>" and "feishu-docs cat <space_id> --max-docs 50") — with output "designed for agent consumption" and options to make docs internet-accessible ("share set ... --public open"), so untrusted third-party content could influence agent decisions.