Unverified50% confidenceCautionExact time
任何要求把文本喂进模型或管道的邀请都应视为潜在风险，切勿将来源不明数据接入生产系统或本地敏感环境
1
Sources
50%
Confidence
Long-term
Relevance
8/11/2026
First Seen
Sources
Related Claims
Unverified从边际风险角度看，如果某项危险信息通过搜索引擎就能找到，模型是否开源对整体安全态势的影响并不显著65% similarUnverifiedA link-based distribution model that lacks a review mechanism may introduce inconsistent application quality and potential security risks.62% similarUnverifiedThe security risk of influencing a model's output behavior by poisoning external documents it reads is known as 'Indirect Prompt Injection.'61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/731085API
curl https://kongchang.com/api/v1/knowledge/claims/731085MCP
get_claim(id=731085)