上周,云安全公司 Sysdig 的研究人员表示,他们记录下了首例已知的“智能体勒索软件”案例。这是一起名为 JadePuffer 的勒索行动,其中由一个 AI 智能体——而非人类——从头到尾负责执行一次真实网络攻击的技术环节。该智能体入侵了存在漏洞的服务器,窃取了凭证,在目标网络中横向移动,加密了文件,甚至自己撰写了勒索信,并像人类黑客一样沿途应对各种障碍。相关报道描述该行动是“在没有任何人类监督下”运行的,“键盘前没有人类操作”。
但这并非全貌。在周一接受 CyberScoop 采访时,Sysdig 公司威胁研究高级总监 Michael Clark 澄清说,人类仍然深度参与其中——只是不参与技术执行环节。Clark 表示:“人类仍然设置并指挥了这次行动,为其背后的基础设施、命令与控制服务器、用于存放被盗数据的暂存服务器进行了配置,并选择了受害者。”他补充道,用于入侵受害者数据库的凭证并非由 AI 智能体自行获取;而是有人通过先前的入侵行为单独获取了这些凭证,并将其交给了该行动。
这些说法与 Sysdig 最初的声明并不矛盾,而该攻击的技术细节本身仍然值得关注——甚至可以说是令人震惊。该智能体通过 Langflow(一款用于构建大语言模型应用的热门开源工具)中的一个已知漏洞进入系统,随后转向一台生产环境 MySQL 服务器,并利用另一个已知漏洞获取了管理员权限。它加密了超过 1300 条配置记录,不仅留下了自己撰写的勒索信,还留下了一个用于支付赎金的比特币地址。Sysdig 尚未披露攻击目标是谁。
这些技术手段显然相当普通,真正引人注目的是其速度和透明度。该智能体在 31 秒内修复了一次失败的登录操作,并全程以自然语言代码注释的形式叙述了自己的推理过程。
一个最初看似让情况变得模糊的细节,现已得到澄清。克拉克曾告诉 CyberScoop,Sysdig 发现“攻击中使用了多个模型”,并引用了窃取到的 OpenAI、Anthropic、DeepSeek 和 Gemini 的密钥——这种表述留下了疑问,即是否有多个模型积极驱动了入侵的不同阶段。在要求澄清时,克拉克告诉 TechCrunch,这些密钥只是该智能体窃取的部分内容,并非驱动它的证据。
“该智能体在 Langflow 主机上扫描了所有有价值的东西——提供商 API 密钥、云凭证、加密货币钱包和数据库配置——而这些提供商密钥只是战利品的一部分,”他通过电子邮件表示。“它们表明了攻击者认为值得拿走的东西,但并不能告诉我们哪个模型在做决策。”
关于实际驱动 JadePuffer 的模型,克拉克表示 Sysdig“无法识别驱动该智能体的具体模型”,并且对其系统提示词或配置一无所知。
微软研究员杰夫·麦克唐纳几天前在 LinkedIn 上提出的理论,值得在此背景下重新审视。基于自己的红队测试经验——该经验显示前沿实验室的安全层表现良好——麦克唐纳怀疑,这次攻击背后是一个去除了安全训练的开放权重模型,而非前沿模型。Sysdig 自身的说法既未证实也未排除这种可能性。
麦克唐纳的帖子还警告说,勒索软件攻击活动现在主要受限于攻击者的预算,而非人力,这增加了“同时进行数千或数万次攻击活动”的可能性。这种担忧与克拉克周一描述的情况有些难以吻合。(如果每次操作仍需人工选择受害者、配置基础设施并获取数据库凭证,那至少会形成一定的瓶颈。)
无论如何,克拉克告诉 CyberScoop,虽然 Sysdig 尚未看到同一攻击活动波及其他受害者,但考虑到运行一个智能体的成本如此低廉,他预计这种情况将会改变。
Last week, researchers at cloud security firm Sysdig said they’d documented the first known case of “agentic ransomware.” It was an extortion operation, dubbed JadePuffer, in which an AI agent — not a human — handled the technical execution of a real-world cyberattack from start to finish. The agent broke into a vulnerable server, stole credentials, moved through the target’s network, encrypted files, and even wrote its own ransom note, adapting to obstacles along the way like a human hacker would. Coverage of the funding described it as run “without any human oversight,” with “no human at the keyboard.”
That’s not quite the full picture. In an interview on Monday with CyberScoop, Sysdig’s Michael Clark, the company’s senior director of threat research, clarified that a human was still very much involved — just not in the technical execution. “A human still set up and pointed the operation and provisioned the infrastructure behind it, the command-and-control server, the staging server used for the stolen data and chose a victim,” Clark said. The credentials used to break into the victim’s database, he added, weren’t harvested by the AI agent itself; someone obtained them separately, through a prior compromise, and handed them to the operation.
None of this contradicts Sysdig’s original claim, and the technical details of the attack remain notable on their own — wild, even. The agent got in through a known bug in Langflow, a popular open-source tool for building LLM apps, then moved on to a production MySQL server and exploited another known flaw to gain admin access. It encrypted over 1,300 configuration records and not only left behind a ransom note that it wrote itself but it left a Bitcoin address where the ransom could be sent. Sysdig hasn’t disclosed who was targeted.
The techniques were fairly ordinary apparently, what stood out was the speed and transparency involved. The agent fixed a failed login in 31 seconds, narrating its own reasoning in natural-language code comments the whole way.
One detail that initially seemed to muddy the picture has since been clarified. Clark had told CyberScoop that Sysdig found “multiple models were used in the attack,” citing harvested keys for OpenAI, Anthropic, DeepSeek, and Gemini — language that left open the question of whether several models actively powered different stages of the intrusion. Asked to clarify, Clark told TechCrunch that those keys were simply part of what the agent stole, not evidence of what was driving it.
“The agent swept the Langflow host for anything valuable — provider API keys, cloud credentials, cryptocurrency wallets, and database configs — and those provider keys were part of the loot,” he said via email. “They are indicative of what the attacker considered worth taking, but they do not tell us which model was making the decisions.”
On the model actually running JadePuffer, Clark said Sysdig “was not able to identify the specific model driving the agent” and has no visibility into its system prompt or configuration.
Microsoft researcher Geoff McDonald’s theory, offered on LinkedIn several days ago, is worth revisiting in that light. McDonald suspected an open-weight model with safety training stripped out, rather than a frontier model, was behind the attack, based on his own red-teaming experience showing frontier labs’ safety layers hold up well. Sysdig’s own account doesn’t confirm or rule that out.
McDonald’s post also warned that ransomware campaigns are now bounded primarily by attacker budget rather than human effort, raising the possibility of “thousands or tens of thousands of simultaneous campaigns.” That concern is a little harder to square with what Clark described Monday. (If a human still has to choose each victim, provision infrastructure, and obtain database credentials for every operation, that’s a bit of a bottleneck, at least.)
Either way, Clark told CyberScoop, while Sysdig hasn’t seen the same operation hit other victims yet, given how cheap it is to run an agent, he expects that to change.