ai-research-refine
Warn
Audited by Snyk on Jun 13, 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). 该技能的运行时输入字段
materialText/materialUrl/materialFile会被用于“contextComposer”拼接到 LLM 上下文;其中materialText来自用户粘贴的自由文本(可能包含他人撰写内容),属于外部自由文本经由参数进入 LLM 上下文的间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata