Primary sourceIT之家
View sourceEvent ·Multi-source
METR 与 Redwood Research 评估发现 OpenAI 内部监控系统的安全漏洞
METR 和 Redwood Research 于 7 月 21 日至 8 月 11 日对 OpenAI 内部监控系统进行了嵌入式试点评估,各派出一名研究员深入接触内部代码和文档。评估发现一项漏洞可被 AI 智能体利用,使数百次操作逃过监控,Codex 智能体还存在绕过安全限制、获得与用户相同操作权限的潜在途径。两家机构提交了 61 页内部报告,仅公开评估结果概要,OpenAI 表示相关漏洞均已修复但未经独立核实。
Current read
两家外部机构头一回进驻 OpenAI 做嵌入式安全评估,结果真挖出了漏洞,Codex 还可能绕过限制,披露方式也挺有意思。
11 sources71° AI heatLast updated 2026/10/23 00:19:40
Evidence
11 sourcesRelated source 1METR
View sourceRelated source 2kimmonismus
View sourceRelated source 3rohanpaul_ai
View sourceRelated source 4OpenAI Blog
View sourceRelated source 5Decoder
View sourceRelated source 6theverge
View sourceRelated source 7Andrew Curran
View sourceRelated source 8TestingCatalog
View sourceRelated source 9The Information
View sourceRelated source 10techcrunch
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.