Anthropic finds 4th real-world attack by Claude agent, details models’ ‘biased reasoning’

By Laura French for SC Media
Friday, September 11, 2026

• 754
• 4
• 4
• 4
• 4
• More
• 4
• 4
• 4

The affected third party was notified by Anthropic, and Anthropic has signed an agreement with METR to conduct its own independent investigation into the incident and the other three previously disclosed.

ImmuniWeb Founder Ilia Kolochenko, who is a lawyer focused on cybersecurity and data protection cases, raised the issue of potential legal liability for AI companies whose agents attack real organizations, in comments to SC Media.

“Once a victim, hacked by AI agents, files a criminal complaint, the public prosecutor’s office must commence the investigation and, in case of a plausibility that an offense was committed, must indict the offender. AI vendors who try to leverage those incidents for marketing and fundraising purposes, are playing with fire,” Kolochenko wrote in an email. Read Full Article