find-skills
Warn
Audited by Snyk on Aug 18, 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). Find Skills 在工作流程中会根据用户原始 Prompt 生成检索词并对 ClawHub 官方仓库/本地已装列表/开源索引进行搜索与读取候选技能的 description 与 metadata(多源检索与技能对比评估),因此若攻击者能在这些被检索/读取的源里投递外部文本内容,LLM 运行时会消化该免费文本。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata