⚡Megatron LLM Hub
←Back to search
Twitter

研究者呼吁 Anthropic 澄清某漏洞在真实网络中的可利用性(IP options 常被中途丢弃)

决定该 AI 服务端漏洞是否需要紧急缓解,实验室可打性与生产环境差异大。
llmrce事件
there is a lot of confusion around this bug. i think it is worth if anthropic clarifies the real world exploitability of this vulnerability, especially given that ip options may be dropped in transit and exploit reliability on production go server on internet may differ.