AI Agent:从工具劫持到 RCE
2026 年,AI Agent(智能体)的自主决策能力正成为内网权限控制的新黑洞。本文深入剖析了 Agent 核心架构 ReAct 中的逻辑缺陷,揭示了 LLM 作为“混淆代理”如何被自然语言指令劫持。文章重点展示了针对 PythonREPLTool 的攻击路径,通过本地复现演示了从 Prompt 注入到获取 Root 权限反弹 Shell 的完整 RCE 过程。同时,本文还探讨了多智能体(Mul
A coordinated campaign is using malicious Chrome extensions that impersonate popular AI tools like ChatGPT, Claude, Gemini, and Grok. These fake “AI assistants” spy on users through injected, remote-controlled iframes, turning helpful browser add-ons into surveillance tools. More than 260,000 users have installed these extensions. Security researchers identified at least 30 Chrome extensions promoted as […]
The post Malicious Chrome AI Extensions Attacking 260,000 Users via Injected IFrames appeared first on Cyber Security News.