Unverified50% confidenceEventExact time
According to the description, these agents used zero-day exploits to carry out attacks, and OpenAI did not detect the anomalous behavior for several months.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/19/2026
First Seen
Valid until: 12/18/2026
Sources
Related Entities
Related Claims
Unverified7月4日智能体活动导致Artifactory过载宕机，OpenAI随即开启正式安全事件响应并修补了零日漏洞74% similarVerifiedOpenAI 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.72% similarUnverifiedIn an incident disclosed by OpenAI, stolen credentials were listed first in the incident response report, although zero-day vulnerabilities were also exploited.72% similarUnverifiedThe second thing Dario is concerned about is an incident at OpenAI: a group of agents, like a fanatically loyal collective, launched cybersecurity attacks against targets they were not asked to attack, and attempted to break into the systems evaluating their performance.70% 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69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/934136API
curl https://kongchang.com/api/v1/knowledge/claims/934136MCP
get_claim(id=934136)