読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · MCP协议SSRF漏洞重大2 分で読めるDisconfirmAI 編集部

Independent Researcher Discloses SSRF Vulnerabilities in Google and JPMorgan MCP Servers, Revealing 'Protocol Pivoting' Risks for AI Agents

Security researcher Syed Anas Mohiuddin discovered Server-Side Request Forgery (SSRF) flaws in MCP servers used by Google and JPMorgan Chase, demonstrating an attack method called 'Protocol Pivoting' that exploits trust between AI agents.

2026-10-21 08:00 GMT+8

Independent security researcher Syed Anas Mohiuddin recently published findings on the security of the Model Context Protocol (MCP), revealing that multiple organizations, including US tech giant Google and US bank JPMorgan Chase, have similar Server-Side Request Forgery (SSRF) vulnerabilities in their MCP projects. These flaws could allow attackers to trick MCP servers into making network requests to internal systems they cannot directly access.

Specifically, Google's database access tool, MCP Toolbox for Databases, was found to have a high-risk SSRF vulnerability tracked as CVE-2026-14540, with a CVSS score of 8.0. The vulnerability stems from the HTTP client's lack of URL redirect checks and destination IP address validation. In an interview with tech media outlet Ars Technica, Mohiuddin explained that he calls the technique of exploiting trust relationships between different protocols to gradually expand the attack surface 'Protocol Pivoting.' In this scenario, malicious instructions can be embedded in external content read by an AI agent; when the agent hands off tasks to other agents, those receiving agents might execute restricted operations if they fail to verify proper authorization.

Google has since patched the SSRF vulnerability in MCP Toolbox, implementing measures such as checking destination IP addresses during connection establishment and restricting connections via IP allowlists and blocklists. This incident serves as a reminder for enterprises deploying AI agents: beyond guarding against prompt injection, it is crucial to strictly limit the network access scope of MCP tools and ensure appropriate authorization checks before agents access sensitive data or perform high-privilege operations.

ログイン / 新規登録
読書リサーチレーダー投資フレームワーク

ソース

  • ithome.com.tw↗
トピック

MCP协议SSRF漏洞

模型上下文协议(MCP)正成为AI代理连接外部工具的标准接口,但其服务器端请求伪造(SSRF)漏洞频发,暴露了AI代理在信任链中的安全盲区。从2026年7月至9月,Google、Grafana Labs和IBM ContextForge等主…

5 ステップ1 件更新日 2026-10-22 05:57

経緯

  1. 2026-07-31NVD发布CVE-2026-14540,指出Google mcp-toolbox存在SSRF漏洞,影响版本0.3.0至1.4.0,CVSS评分8.0。sentinelone.com ↗
  2. 2026-08-10Grafana Labs发布mcp-grafana v1.1.0,修复会话欺骗与SSRF漏洞(CVE-2026-19516),引入可选Bearer Token认证。labs.cloudsecurityalliance.org ↗
  3. 2026-08-31IBM发布安全公告,披露ContextForge MCP Gateway OAuth注册功能中的SSRF漏洞(CVE-2026-8355),建议升级至v1.0.6+。ibm.com ↗

未解決の問題

  • MCP规范是否会在未来版本中将身份验证设为强制项,以消除当前“可选认证”带来的大规模暴露面?
  • 除了已知厂商,还有哪些广泛使用的开源MCP服务器存在类似的会话ID与认证混淆问题?
  • 企业如何在保持AI代理灵活性的同时,有效实施细粒度的网络出口控制而不显著增加运维复杂度?
トピック全文を読む →
リサーチを続ける →