Unverified50% confidenceSolutionExact time

进入LLM上下文的外部内容（如会议转录、上传文档）应视为不可信数据源并进行清洗和隔离

1

Sources

50%

Confidence

Long-term

Relevance

8/12/2026

First Seen

Sources

Zoom AI Assistant Hijacked: Deep Dive into Enterprise AI Integration Security Risks

Related Claims

Unverified仅去除宏和元数据标签但保留文本格式的净化文档仍可能成为隐蔽数据外泄的通道70% similar Unverified对处于资料领取后沉默阶段的用户，更适合以内容价值重新建立联系而非直接推送促销信息63% similar Verified间接提示注入可将恶意指令藏入外部数据源（如网页、文档），待代理读取时自动触发攻击62% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/735464

API

curl https://kongchang.com/api/v1/knowledge/claims/735464

MCP

get_claim(id=735464)