Unverified50% confidenceFactExact time
Prompt injection attacks were first systematically described in 2022 by security researcher Simon Willison.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified提示注入攻击的概念最早由安全研究员 Riley Goodside 于 2022 年 9 月在 Twitter 上公开演示79% similarUnverified依赖混淆攻击由安全研究员Alex Birsan于2021年首次公开披露73% similarUnverified2023年研究人员Simon Willison系统性地揭示了间接提示注入的危害，指出模型具备联网搜索或文件读取能力时攻击面急剧扩大73% similarVerifiedPrompt Injection was first publicly demonstrated by security researcher Riley Goodside in 202273% similarUnverified2023年研究人员Riley Goodside首次系统性演示了间接提示词注入的危害70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/892855API
curl https://kongchang.com/api/v1/knowledge/claims/892855MCP
get_claim(id=892855)