A Defense Contractor Gave Their Personal AI Agent Access to a Secure Pentagon System

First reported by Wired at · Updated · 2 sources

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.

Covered by 2 publishers within 10 hours of the first report.

Summary from Wired.

Reporting2

Wired A Defense Contractor Gave Their Personal AI Agent Access to a Secure Pentagon System · Vittoria Elliott
Cyber Security News Accenture Contractor Allegedly Gave Claude AI Agent Access to Secure Pentagon Network · Guru Baran

Discussion

Hacker News 19 points, 6 comments

Related

Anthropic gives third-party auditors ’employee-like access’ in AI industry first
Anthropic gives six METR staffers internal access to assess frontier AI risks
AI startup claims it hacked Anthropic in 12 hours, gains access to employee details and internal messages
Anthropic’s Claude Mythos 5 AI Agent Tried to Inject Malicious Code and Trick Real Developers

Topics Anthropic