独立研究者 Syed Anas Mohiuddin 测试了 Google、JP Morgan Chase、Weaviate、Rapid7、法国政府跨部门数字局和美国联邦政府等机构的 AI 智能体,发现 MCP(Model Context Protocol)在智能体间通信中存在信任缺口。攻击利用一种特殊形式的提示注入,目标不是 LLM 而是翻译或数据分析等具体智能体,这些智能体内部的护栏往往宽松,会把有害指令沿链条传给下游智能体。
Forever Security's research team disclosed the BragJack attack, using a single ordinary Chromium extension to simultaneously break into five browsers' built-in agents—Gemini Live in Chrome, Perplexity Comet, Microsoft Edge Actions, Opera Neon, and Claude in Chrome—earning a total of $20,000 in bounties and obtaining CVE-2026-0628 and CVE-2026-55945. The core of the attack is Prompt Forcing, using the declarativeNetRequest permission to weaken security response headers like CSP and redirect JavaScript resources, thereby executing code in a privileged context and then directly issuing commands to the agent. Achievable effects include reading local files and browsing history, obtaining browser profile information, taking screenshots of tabs, and in the Gemini Live scenario, accessing the camera and microphone.
The Hacker News 介绍研究者提出的 Agent Data Injection(ADI):攻击者操纵智能体依赖的数据字段,使其在继续执行原任务时依据错误信息采取行动,而不是直接插入新的操作指令。作者在网页操作和编码助手等受控场景中展示了错误点击、误信身份或执行记录等风险,并报告部分针对传统提示注入的防御无法同样阻断这类数据操纵。不同产品和界面设计的结果存在差异,例如随机化元素标识可限制某类点击攻击;更严格的数据来源追踪也伴随任务完成能力下降。报道基于研究者实验及访谈,不代表存在已确认的在野利用,也不能将单项防御结果泛化为全面安全。