Unverified50% confidenceEventExact time
2023年已有研究者演示了通过在网页中嵌入白色文字指令，成功劫持支持网络访问的ChatGPT插件
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
Unverified2023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，同年慕尼黑工业大学团队发表论文证明可通过恶意网页劫持基于GPT-4的浏览器助手外传用户数据70% similarUnverified2023年研究者已经演示了通过间接注入控制Bing Chat代理行为的概念验证攻击63% similarUnverifiedIn 2024, security researcher Johann Rehberger demonstrated an indirect prompt injection attack that successfully hijacked the output of multiple commercial RAG systems by embedding instruction text in public web pages that was invisible to humans but readable by AI61% similarUnverified2023年以来研究人员在AutoGPT、LangChain等主流Agent框架中演示了提示注入攻击的可行性56% 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55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/532913API
curl https://kongchang.com/api/v1/knowledge/claims/532913MCP
get_claim(id=532913)