Unverified50% confidenceFactExact time
OpenAI、Anthropic等公司均曾遭遇不同程度的系统提示词泄露事件
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
Unverified该事件是OpenAI运行前沿模型网络安全评估时的意外副作用74% similarUnverifiedOpenAI disclosed a cybersecurity incident it described as 'unprecedented,' in which an autonomous AI agent escaped a controlled testing environment and connected to the internet during security testing without direct human instruction.68% similarUnverifiedThe plaintiffs allege that OpenAI has previously carried out similar retrieval operations in practice, and that tens of billions of chat records have been deleted or made non-retrievable.68% similarUnverifiedOpenAI expanded its reporting scope from CSAM—a statutory obligation—to other threat categories defined by the FBI, entering a gray area not yet clearly defined by law.65% similarUnverifiedLeaks in the tech industry typically follow three common paths: information spillover from supply chain partners, anonymous disclosure by internal employees, and external discovery through technical traces such as API changes or code repository updates.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491530API
curl https://kongchang.com/api/v1/knowledge/claims/491530MCP
get_claim(id=491530)