lark-base

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

• Third-party content exposure detected (low risk: 0.10). The workflow consumes data from a Lark Base table via a database query DSL (lark-cli base +data-query), which executes a user-provided or application-driven query where content from text fields is treated as query input and returned in the result set for LLM consumption.