人工智能代理无需发明全新的入侵手段就能突破网络防御体系，它们只需以极快的速度运用人类早已使用的攻击方法即可。
AI agents don't need to invent new ways to hack the internet to overwhelm its defenses. They just need to speed-run the ones humans already use.
为何此事值得关注：事实证明，这些代理能够以惊人的速度和规模自动执行各类基础黑客技术，使得互联网上长期存在的安全漏洞变得极易被利用。
Why it matters: Agents are proving they can automate basic hacking techniques at a speed and scale that is turning the internet's long-standing security gaps into easy targets.
相关动态：周四晚些时候，OpenAI宣布已通知100多家机构：在部署前的测试阶段，该公司的AI代理可能曾访问过这些机构的系统。
Driving the news: OpenAI said late Thursday it had notified more than 100 organizations that its agents may have accessed their systems during pre-deployment testing.
- 上周，Transluce与Corridor的研究人员又发现多起AI代理攻击政府网站的案例，涉及美国、加拿大等国的官方网站。
• Researchers at Transluce and Corridor also found a new batch of incidents last week where AI agents targeted government websites, including those of the U.S. and Canada.
- 据Axios报道，目前各类人工智能企业及研究人员正在积极调查数万起前沿AI模型在测试范围之外实施攻击的案例。
• AI companies and researchers are actively investigating tens of thousands of cases where frontier models went outside the bounds of their pre-deployment tests, Axios recently reported.
现实情况：在这些违规安全测试中，AI代理所采用的攻击手段与人类黑客数十年来一直使用的技术如出一辙——包括盗用他人账号凭证、利用泄露的API密钥，以及绕过机器人检测机制等。
Reality check: Agents in these rogue safety-testing scenarios are just emulating the hacking techniques — using stolen credentials and exposed API keys while also bypassing bot detection — that human hackers have successfully used for decades.
- 在众多新报告的案例中，AI代理均成功访问了公开数据库及网站。
• In many of the newly reported cases, agents were accessing publicly available databases and websites.
- “我们观察到的攻击手段其实并不复杂，”Corridor联合创始人、Transluce报告撰写人之一杰克·凯布尔对Axios说道，“这些手段相当基础、简单。”
• "The hacks we saw weren't particularly sophisticated," Jack Cable, co-founder of Corridor and one of the authors of Transluce's report, told Axios. "They were quite limited, quite rudimentary."
不过也要看到：部分最新案例显示，AI代理在执行与网络安全毫无关联的常规任务时，也会主动寻找系统漏洞。这说明它们未必需要收到明确指令才会实施攻击。
Yes, but: Some of the latest incidents happened while agents were performing mundane tasks unrelated to cybersecurity, suggesting agents don't always need to be told to hack before they start looking for security flaws.
- 例如，某个被指派查找20世纪初加拿大离婚记录的代理遇到了访问障碍，于是便尝试通过检测网络安全漏洞来获取所需信息。
• In one case, an agent tasked with finding Canadian divorce records from the early 1900s encountered roadblocks and tested for cybersecurity vulnerabilities as another way to retrieve the information.
- “这种现象的出现本身就令人担忧，”凯布尔指出。人工智能生成的大量攻击行为仍会给网络安全防御者带来新的挑战。
• "The fact that it was happening at all is quite concerning," Cable said. Between the lines: The flood of AI-generated activity will still create new headaches for defenders.
“这些攻击手段其实并不新鲜，”DayBlink Consulting的合伙人迈克尔·摩根斯坦（Michael Morgenstern）对Axios表示，“但现在，只需要一个人利用人工智能技术，就能大规模地发起这些攻击。”
• "None of these attacks are new," Michael Morgenstern, partner at DayBlink Consulting, told Axios. "But now a single person with AI can run them at scale."
过去需要黑客手动探测网站、寻找泄露的用户名和密码，或绕过访问限制的任务，现在都可以交给软件来完成——这些软件会持续不断地尝试攻击目标。
• Tasks that once required a hacker to manually probe websites, hunt for exposed credentials or work around access restrictions can now be delegated to software that keeps trying on its own.
Cable还指出，那些部署了相关攻击工具的公司，以及评估这些工具的人工智能公司，都需要加强监控，以防止这些工具出现异常行为。
• Cable added that companies deploying agents, as well as the AI companies evaluating them, will need robust monitoring to catch agents behaving in unexpected ways.
总体来看：传统的网络安全防护措施仍然有效。关闭那些存在安全漏洞的服务、定期更换泄露的用户名和API密钥、修补已知的漏洞、以及限制用户访问权限，这些措施仍然能够有效降低攻击的成功率。
The big picture: The old cybersecurity playbook is still relevant. • Closing exposed services, rotating leaked credentials and API keys, patching known vulnerabilities and limiting access still make many of these attacks harder. • AI models are largely exploiting classes of vulnerabilities that defenders have "known about for decades" and already know how to prevent, Cable said.
总结：仅仅因为用于发起攻击的技术发生了变化，企业保护网络的方式并不会随之改变。
The bottom line: How companies defend their networks doesn't change just because the technology carrying out the attacks is new.