LesenForschungRadarAnlageframework
Anmelden / Registrieren
← Zurück zur Lektüre
NewsThema · CathedralWesentlich2 Min. LesezeitDisconfirmAI Redaktion

US AI Startup Cathedral Claims Autonomous Agents Hacked Anthropic in Under 12 Hours via Third-Party Software Flaws

US-based AI security startup Cathedral claims its autonomous agents breached Anthropic's systems in under 12 hours by exploiting third-party software weaknesses, accessing HR, sales, and IT data; Anthropic confirmed limited access and terminated it same day.

2026-10-28 23:25 GMT+8

US-based AI security startup Cathedral claims that its deployed autonomous AI agents successfully breached the internal systems of another leading AI company, Anthropic, in less than 12 hours. According to TechRadar, the Cathedral team initially attempted manual penetration testing without success before deploying AI agents, which found an entry point by exploiting weaknesses in third-party business software.

After gaining access, the agents accessed data from Anthropic's human resources, sales, and IT systems, including meeting transcripts, salary information, job offers, and Slack messages. Anthropic confirmed the incident, stating that Cathedral accessed a "limited set" of sales, human resources, and IT systems, compromising contact information and basic user account records belonging to certain customers and partners. Anthropic emphasized that source code and AI model weights were not accessed, and that its monitoring flagged some of Cathedral's activity before they reported it, shutting off their access the same day.

Cathedral was founded by former members of the US Department of Government Efficiency (DOGE) and focuses on offensive and defensive cyber operations for the US military and government. The attack was reported through Anthropic's bug bounty program on HackerOne. However, according to Gizmodo, Anthropic accused Cathedral of violating the program's rules by failing to disclose the full extent of its activity, which could potentially block the bounty payment.

Anmelden / Registrieren
LesenForschungRadarAnlageframework

This incident highlights the vulnerability of enterprise supply chain security: even with strong internal defenses, weaknesses in third-party integrated software can be rapidly exploited by AI-driven attackers. The Washington Post cited Cathedral's report as saying that weaknesses in ordinary enterprise software can compromise the infrastructure of even the most advanced organizations, serving as a wake-up call for every company.

Quellen

  • techradar.comTechRadar↗
Thema

Cathedral

美国AI安全初创公司Cathedral声称其自主智能体在不到12小时内通过第三方软件漏洞入侵了Anthropic的内部系统,获取了包括HR、销售数据及Slack消息在内的敏感信息。Anthropic确认访问范围有限且已切断连接,但反驳称攻击…

3 Schritte1 BeiträgeAktualisiert 2026-10-29 21:05

Wie es dazu kam

  1. 2026-10-26Anthropic向美国证券交易委员会提交IPO文件,估值预期巨大;同日,Cathedral的测试报告被《华盛顿邮报》审阅。independent.co.uk ↗
  2. 2026-10-28TechRadar等媒体报道Cathedral声称其AI智能体在12小时内通过第三方业务软件漏洞入侵Anthropic,获取员工薪资、会议记录及Slack消息。techradar.com ↗
  3. 2026-10-29Anthropic回应称监控系统在Cathedral报告前已标记部分活动,并于当天切断访问;同时指出攻击尝试实际持续数天,且Cathedral行为超出漏洞赏金计划范围。the-decoder.com ↗

Was noch ungeklärt ist

  • Anthropic是否会因Cathedral违反披露规则而拒绝支付漏洞赏金?
  • 受影响的具体第三方软件供应商是谁,以及这些漏洞是否已被彻底修复?
  • 前OpenAI员工Will Depue关于Cathedral获得Slack管理员权限的说法是否属实,Anthropic是否会进一步公开细节?
Vollständiges Thema lesen →
Recherche fortsetzen →