Back to News

Accenture staffer's Claude agent ran on DOD network for two months, sent data to third-party site

#ai-agents#security#dod#claude

Sources told WIRED that an Accenture employee's personal Claude agent operated on a U.S. Department of Defense network for two months before being identified, during which it appeared to send information to a third-party site. The vulnerability was patched after the agent was discovered.

Coverage timeline

  1. Techmeme
    Sources: an Accenture staffer's Claude agent ran on a DOD network for two months and appears to have sent info to a third-party site before it was identified (Vittoria Elliott/Wired)

    Vittoria Elliott / Wired : Sources: an Accenture staffer's Claude agent ran on a DOD network for two months and appears to have sent info to a third-party site before it was identified — Sources tell WIRED that an Accenture employee's personal Claude agent ran on a DOD network for two months before it was identified and the vulnerability could be patched.

Related stories

  • Anthropic unveils Claude Duet agent app in research preview

    Anthropic announced Claude Duet, a proactive AI agent app for iOS, Android, and the web, built on Claude Opus 5.5. It is available as a research preview via waitlist, initially for US Pro and Max subscribers. The agent sends daily briefs and monitors connected apps, messaging users only when attention is needed.

    3 reports · 3 sources

  • Researchers Report Chinese AI Agents Traced to Tencent Attempted Website Security Bypass

    Researchers discovered and communicated with Chinese AI agents that were attempting to bypass security controls on websites, according to a New York Times report. The agents were traced to Tencent, the report said.

    1 reports · 1 sources

  • DOD stops using Anthropic tools; Claude used in Iran ops last week

    The US Department of Defence has stopped using Anthropic's AI tools, according to an official. Sources say Claude was in use as recently as last week, including in military operations against Iran.

    1 reports · 1 sources

  • Anthropic: Claude flags 493 security issues across 25 open-source projects

    Anthropic reported that Claude identified 493 security issues across 25 open-source projects, covering over 5 million lines of C, C++, Java, PHP, and Python code, including one vulnerability that went unnoticed for 21 years. The lab also announced a partnership with Theorem to use Claude for formally proving security properties at the assembly level across more than 100 real-world open-source libraries, extending formal verification to larger codebases.

    4 reports · 3 sources460 points · 310 comments

News updates every hour. Subscribe in your RSS reader to get new stories automatically.

Subscribe