安全研究者 Thomas Roccia 披露，攻击者使用 Claude Code 智能体攻击 Solana 验证节点和 MEV 机器人服务器，窃取私钥并转走钱包资金。该行动使用名为 MevBotResearch 的项目，配置了两个定制智能体。
据研究者介绍，攻击方从 Solana 网络节点信息、GitHub 和 npm 收集了约 5,900 个 IP，构成其目标池，并搜寻暴露在互联网上的数据库、容器管理、监控及远程访问服务。
在研究者报告的一起确认攻击中，攻击方利用暴露服务和配置问题获得权限，随后窃取私钥并转移钱包资金。
Roccia 还称，攻击方会以“获授权的红队演练”为由，向 GLM 委派任务。这起行动将编码智能体和多模型任务协作用于基础设施入侵与资产盗窃。
原帖留影
🧐 We identified a new crypto theft campaign that uses Claude Code agents to attack Solana validators and MEV-bot servers and steal private keys and drain wallets! @SecurityBreakAI The operation uses a project called MevBotResearch, with two custom agents defined in .claude/agents/: hunter.md and exploiter.md. The agents target approximately 5,900 IPs collected from Solana gossip data, GitHub and npm. They search for exposed ClickHouse, Redis, Docker, Grafana, Solana RPC and SSH services. In one confirmed attack: - They accessed a passwordless ClickHouse instance and abused url() for SSRF. - Escalated to root through a misconfigured logrotate service. - Stole private keys from /home/sol/keys and drained wallet balances above 0.02 SOL in approximately 5 seconds. The attackers also delegate tasks to GLM, under the pretext of an "authorized red-team engagement". If you operate Solana infrastructure, review your exposed services, SSH access and private keys stored on internet-facing systems. IOCs in next tweet 👇@fr0gger_在 X 查看原帖发布于 2026/11/12 08:57（北京时间）