←搜索结果

按匹配度 · 共 62 条结果 清除搜索

星期六

  1. Johann Rehberger / Embrace The Red

    MCP 安全风险与利用链:不可信服务器与困惑的客户端

    安全研究者 Johann Rehberger 详细分析 MCP 的安全风险,指出仅将恶意工具服务器加入对话上下文即可劫持会话,无需实际调用工具。他演示了在工具元数据中嵌入隐藏 Unicode Tags 指令的端到端利用链,使 Claude 在用户界面看不到异常的情况下先调用 enter_matrix 工具,再执行用户请求的 message_of_the_day。作者称该 Claude 遵循隐藏 Unicode Tag 指令的问题早在 14 个月前就已负责任披露给 Anthropic,但未被视为安全漏洞,此次 MCP 弱点也在数周前告知 Anthropic 且仅得到可复现的回复。他建议不要随意连接不可信 MCP 或 OpenAPI 工具服务器,并检查代码、接口定义与隐藏指令。

    they all suffer from prompt injection and confused deputy threats. Many of the exploits we have discussed in the past involved tool invocation, from Zapier and ChatGPT exploits to Microsoft Copirate exploit to search email before leaking them, all of these required to know what tools are accessible and how to invoke them. So I figured, I spend some time explaining how I go about debugging and discovering things, in this case with MCP. Anthropic discusses prompt injection and other risks in their

    匹配字段正文

星期三

  1. Cato AI Labs精选

    Aim Labs 披露 Cursor 经 MCP 自动启动触发远程代码执行漏洞 CurXecute

    Aim Labs 在 Cursor IDE 中发现高危漏洞 CurXecute,可导致完整的远程代码执行,编号 CVE-2025-54135,严重性评级 8.6。攻击路径是:当 Cursor 接入会读取外部内容的 MCP 服务器(如 Slack)时,一条被投毒的提示词就能诱导智能体改写 ~/.cursor/mcp.json;而 Cursor 会立即执行该文件新增的条目,并在用户确认前就写入磁盘,从而以用户权限执行攻击者命令。Cursor 已在 1.3 版本修复,更早版本仍受影响。

    ls remain essential even after patches and Aim Security supplies these state of the art protections. In June we disclosed EchoLeak, the first zero‑click exfiltration chain against Microsoft 365 Copilot. It proved that untrusted content (a single inbound e‑mail) could hijack an LLM’s inner loop and leak whatever data the model could see - without user action. EchoLeak underscored another critical lesson: if outside context can steer an AI-agent, any agent can have its control flow hijacked and it

    匹配字段正文