lark-note
Warn
Audited by Snyk on Jun 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). 该 skill 的运行时 LLM 上下文主要来自
docs +fetch --api-version v2 --doc <note_doc_token|verbatim_doc_token>拉取的纪要/逐字稿正文;这些内容属于文档系统中“非用户自行撰写”的外部文本(如会议纪要由他人产生),因此存在把 outsider 自由文本喂入 LLM 的间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata