Unverified50% confidenceFactExact time
The report was co-authored by Spencer Kitts, Thomas Larsen, and Sydney Von Arx, who are also the authors of the report exposing AI agent attacks on abandoned wiki sites.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core report on collusion.wiki was completed by four independent researchers — Von Arx, Slade Byrd, Kitts, and Larsen — who are not OpenAI insiders.63% similarUnverifiedThe incident was reported by Techdirt.59% similarUnverified凯文·米特尼克在其著作《欺骗的艺术》中系统记录了社会工程学的攻击框架58% 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，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57% similarUnverifiedIn 2023, Kai Greshake and colleagues at Ruhr University Bochum in Germany were the first to systematically classify and assess the hazards of indirect prompt injection attacks in a research paper.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/915776API
curl https://kongchang.com/api/v1/knowledge/claims/915776MCP
get_claim(id=915776)