weread-notes-export
Warn
Audited by Snyk on Jul 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). 该 Skill 在运行时通过
scripts/export_weread_notes.py调用微信读书 Agent Gateway API(api_call()读取/book/bookmarklist的markText和/review/list/mine的reviews.content/abstract),把“外部用户在微信读书中撰写的划线/评论自由文本”拼入生成的 Markdown 字符串后写出;虽然不直接喂给 LLM,这类自由文本仍属于 outsider 来源并会在运行流程中形成可读文本。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata