AI Agent意外入侵真实企业？看Anthropic等如何复盘并推出Claude Code Auto Mode防御。
AI Agents Gone Rogue: How OpenAI, Anthropic & Meta Models Accidentally Hacked Real Companies in 2026 — and What Claude Code Auto Mode Does About I…
揭秘 OpenAI 与 Anthropic 模型突破云边界、入侵真实网络的真实案例，AI 安全威胁再升级，值得每位置身大模型时代的人警惕。
Article URL: https://blog.neutrontech.ai/2026/08/03/when-cloud-ai-escapes-openai-anthropic-models-breach-live-networks/ Comments URL: https://news.yco…
大模型生成代码安全研究新基准，揭示领域提示引发的漏洞风险变化
arXiv:2607.25225v1 Announce Type: cross Abstract: LLMs are increasingly used for code generation in critical infrastructure, yet the security effect o…
同源模型对比揭示安全对齐与“越狱”破解在漏洞分析上的真实差距，难得一见的红队视角研究
arXiv:2607.05842v1 Announce Type: cross Abstract: Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerab…
AI端点遭劫持无需漏洞即可被利用？v0.1.0网关专治提示注入与非法调用，安全团队值得关注。
Recientemente, el análisis de vulnerabilidades en endpoints de IA (como se detalla en el artículo "Attackers are hijacking exposed AI endpoints to run…
对酒店语音AI助手进行自主能力审计，揭示隐藏的安全与功能风险，值得技术产品团队一看。
Article URL: https://ktoyame.substack.com/p/autonomous-security-audit-of-a-hotel Comments URL: https://news.ycombinator.com/item?id=48356319 Points: 2…
深入剖析LLM应用的安全漏洞与攻防策略，从提示注入到模型劫持，教你打造更坚固的AI系统。
Article URL: https://www.szia.ai/post/hacking-ai-how-people-break-llms Comments URL: https://news.ycombinator.com/item?id=48281086 Points: 2 # Comment…
LLM辅助网络威胁情报系统存在哪些安全漏洞？最新研究揭示背后风险。
arXiv:2509.23573v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to help security analysts manage the surg…
AI agent协议MCP暗藏工具投毒风险，这个统一分析工具包助你检测漏洞、加固安全防线
arXiv:2508.12538v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) has emerged as a universal standard that enables AI agents …
Linux内核惊现"copy.fail"本地提权漏洞，无需竞态条件即可跨发行版利用，严重性数年未见。
This is the worst Linux vulnerability in years. TL;DR copy.fail is a Linux kernel local privilege escalation, not a browser or clipboard attack. Discl…