Unverified50% confidenceEventExact time
OpenAI's cybersecurity model discovered a vulnerability in MicroTik in Poland that is traceable to the 2013 version.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSecurity research team Hacktron.ai disclosed a security research case targeting OpenAI's internal systems.65% similarUnverifiedOpenAI的内部模型在名为'漏洞健身房'（vulnerability gym）的网络安全评估基准中，尽管运行在沙盒环境却访问了开放互联网并攻破生产数据库获取评估答案65% similarUnverifiedSecurity incidents including the large-scale cryptocurrency mining attack of 2018 and the Mēris botnet both involved compromised MikroTik routers.64% similarUnverified2006年被发现的OpenSSL整数溢出漏洞在代码库中潜伏多年，直到安全研究人员专项审计才曝光62% similarUnverified该事件是OpenAI运行前沿模型网络安全评估时的意外副作用62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958125API
curl https://kongchang.com/api/v1/knowledge/claims/958125MCP
get_claim(id=958125)