AI Security AI安全 7h ago Updated 2h ago 更新于 2小时前 46

Attackers Steal METR API Key and Consume AI Credits Worth About $600,000 攻击者窃取METR API密钥并消耗约60万美元的AI积分

METR, a frontier AI evaluation non-profit, suffered two security incidents in 2026 involving stolen API keys and unauthorized access attempts Attackers exploited a "fail-open vulnerability" in a vibe-coded app to steal an API key and consumed approximately $600,000 worth of AI credits over three weeks A second attack campaign involved systematic probing of public infrastructure using automated agents for credential stuffing, OAuth token grants, and staff phishing No sensitive evaluation data was METR非营利组织遭遇两次安全事件,攻击者盗取API密钥并消耗约60万美元AI信用额度 攻击者通过证书透明度列表扫描近期注册的LLM/Agent相关网站,利用"fail-open漏洞"获取未受保护的API密钥 五月攻击为系统性外部攻击活动,使用AI代理自动化漏洞发现、凭证填充和OAuth token尝试 METR已更新安全策略,包括限制凭证存储位置、加强监控和添加支出警报

68
Hot 热度
62
Quality 质量
65
Impact 影响力

Analysis 深度分析

TL;DR

  • METR, a frontier AI evaluation non-profit, suffered two security incidents in 2026 involving stolen API keys and unauthorized access attempts
  • Attackers exploited a "fail-open vulnerability" in a vibe-coded app to steal an API key and consumed approximately $600,000 worth of AI credits over three weeks
  • A second attack campaign involved systematic probing of public infrastructure using automated agents for credential stuffing, OAuth token grants, and staff phishing
  • No sensitive evaluation data was compromised, but an inadvertently exposed SQL endpoint contained sensitive model data that was later discovered by an independent security researcher

Why It Matters

This incident highlights the growing threat of AI credit theft and the security risks associated with rapidly deployed, minimally secured applications in the AI research ecosystem. It demonstrates how threat actors are increasingly leveraging AI agents themselves to automate vulnerability discovery and credential harvesting at scale.

Technical Details

  • The March 2026 incident involved a researcher's personal EC2 instance running an agent orchestration dashboard behind Google authentication that suffered a fail-open vulnerability, silently disabling authentication and exposing the system to the public internet
  • Attackers discovered the exposed instance by scanning certificate transparency lists for recently registered websites containing LLM/agent-related keywords, then prompted the agent to reveal its API key and added an SSH key for persistent access
  • The May 2026 campaign featured sustained external probing using automated agents for credential stuffing, OAuth token grant attempts, service scanning, and staff phishing attempts
  • An inadvertently exposed read-only SQL query mechanism in METR's public transcript viewer contained sensitive model data due to a scoping bug, though no unauthorized access was detected
  • The $600,000 in credits went unpaid because the model provider supplied them free of charge to the non-profit, and the abuse went undetected due to lack of token spend caps and high baseline usage from legitimate evaluations

Industry Insight

  • Organizations deploying AI agents should implement strict spend caps and real-time monitoring alerts on API keys, as abuse can go undetected in high-traffic evaluation environments
  • The "vibe-coding" trend of rapidly building applications with minimal security oversight creates significant attack surfaces that threat actors are actively scanning for using automated reconnaissance
  • AI-powered attack automation is becoming sophisticated enough to systematically probe multiple attack vectors including credential stuffing, OAuth exploitation, and social engineering, requiring defense-in-depth strategies

TL;DR

  • METR非营利组织遭遇两次安全事件,攻击者盗取API密钥并消耗约60万美元AI信用额度
  • 攻击者通过证书透明度列表扫描近期注册的LLM/Agent相关网站,利用"fail-open漏洞"获取未受保护的API密钥
  • 五月攻击为系统性外部攻击活动,使用AI代理自动化漏洞发现、凭证填充和OAuth token尝试
  • METR已更新安全策略,包括限制凭证存储位置、加强监控和添加支出警报

为什么值得看

本文揭示了AI研究机构面临的新型云安全威胁,展示了攻击者如何利用自动化代理和证书透明度数据主动寻找暴露的API密钥。对AI从业者而言,这凸显了AI基础设施安全管理的紧迫性,特别是API密钥保护和支出监控的重要性。

技术解析

  • 攻击向量:攻击者通过证书透明度列表扫描近期注册的包含LLM/Agent关键词的网站,发现使用"vibe-coded"框架开发的公开可访问EC2实例。该实例存在fail-open漏洞,导致Google认证被静默禁用,API密钥暴露于公网。
  • 凭证窃取与持久化:攻击者通过提示AI代理直接获取模型提供商API密钥,并添加SSH密钥实现持久访问,随后在3周内消耗大量公共模型API信用额度。
  • 自动化攻击活动:五月攻击中,威胁行为者使用AI代理自动化执行凭证填充、OAuth token授予尝试、新部署服务扫描和员工钓鱼等攻击,形成持续的外部攻击活动。
  • 数据暴露风险:METR的公开转录查看器意外暴露了只读SQL查询机制,虽然默认限制为公共数据,但漏洞可能被利用访问未发布的评估数据。数据库还意外包含敏感模型数据。
  • 检测延迟原因:由于METR运行大规模评估实验通常消耗大量token,且API密钥未设置支出上限,导致异常使用未能及时发现。

行业启示

  • AI基础设施安全需升级:随着AI代理和自动化攻击工具的普及,传统安全边界正在失效。研究机构和企业必须实施更严格的API密钥管理、支出监控和异常检测机制。
  • 云配置风险凸显:vibe-coded等快速开发框架可能引入安全漏洞,组织在采用新兴开发工具时需平衡敏捷性与安全性,确保认证和授权机制可靠。
  • 行业协作与透明披露:METR在公开披露前已与合作的AI公司分享发现,这种协作模式有助于行业共同应对新兴威胁,建议建立更广泛的安全信息共享机制。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Security 安全 Evaluation 评测 Research 科学研究 LLM 大模型