Research · Thursday 22 October 2026 · story 10
CrowdStrike says hackers bypass AI guardrails in autonomous attacks
WIRED reports that CrowdStrike found four threat groups bypassed AI safeguards and ran autonomous attacks with Claude and Deepseek models. The researchers said one Spanish and English actor compromised at least 15 Argentine health care organizations.
Why it matters. This shows agent operators cannot rely on model guardrails alone when Claude and Deepseek can be routed around safeguards in autonomous attacks.
Read the original at wired.com