skill-slimming
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). source/feed: 本地 loopback 复审运行时
scripts/review_server.py在serve → /api/bootstrap与用户提交的/api/state读取/回传 JSON 字段（其中包含由外部页面/用户交互可能携带的自由文本如 notes、项目名、触发词等），这些文本会进入 LLM 可用的“状态读取”路径review_server.py read。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata