Anthropic reports fourth cybersecurity incident with early version of Claude

FILE PHOTO: Anthropic logo, a keyboard, and a robotic hand in this illustration taken June 5, 2026.

FILE PHOTO: Anthropic logo, a keyboard, and a robotic hand in this illustration taken June 5, 2026. (REUTERS/Dado Ruvic/Illustration/File Photo)


1 photo
Save Story

Estimated read time: Less than a minute

Sept 9 — Anthropic said on Wednesday it ​had identified a fourth cybersecurity incident involving an early version of ‌its Claude AI model.

The company said in ⁠a blog post ​the incident occurred ⁠in January and involved an ‌early version of ‌Claude Opus 4.6. It has ⁠notified all the ⁠affected parties but did not disclose more details.

Anthropic had disclosed in July some of its Claude AI models had hacked into the ‌systems of three companies ​during cybersecurity tests.

AI companies are under scrutiny over AI breakout events, including cases where AI agents have inadvertently been unleashed on to the open internet.

Over the past week, ​Reuters reported that rogue agents ‌from OpenAI ‌hijacked ⁠a German-language wiki and a host of other sites — an incident OpenAI chose not to disclose until ‌the news agency ​made it public.

(Reporting ‌by Mariam Sunny ⁠in ​Bengaluru; Editing by Tasim Zahid and Arun ​Koyyur)

Photos

Most recent Science stories

Related topics

Reuters

    STAY IN THE KNOW

    Get informative articles and interesting stories delivered to your inbox weekly. Subscribe to the KSL.com Trending 5.
    By subscribing, you acknowledge and agree to KSL.com's Terms of Use and Privacy Notice.
    Newsletter Signup

    KSL Weather Forecast

    KSL Weather Forecast
    Play button