Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations

Anthropic on Thursday became the latest artificial intelligence (AI) company to reveal that three of its models, including Claude Opus 4.7, Mythos 5, and an unnamed research model, had breached three unnamed organizations during cybersecurity testing without its knowledge.

The AI firm said the earliest incidents date back to April 2026, adding it made the discoveries after launching a “

Source: The Hacker News

Leave a Reply

Your email address will not be published. Required fields are marked *

Explore More

Critical FortiMail Zero-Day Flaw Exploited in Attacks Allows Unauthenticated Arbitrary File Writes

Critical FortiMail Zero-Day Flaw Exploited in Attacks Allows Unauthenticated Arbitrary File Writes The U.S. Cybersecurity and Infrastructure Security Agency (CISA), on Thursday, added a critical security flaw impacting Fortinet FortiMail

DPRK-Linked macOS Malvertising Uses Fake Updates to Deliver Crypto-Stealing Malware

DPRK-Linked macOS Malvertising Uses Fake Updates to Deliver Crypto-Stealing Malware Threat actors with ties to North Korea have been attributed to a sophisticated macOS malvertising campaign that involves redirecting users

Attack Update: Top 5 Attack-IPs auf doode.info – 07.09.2026

Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. 94.154.46.245 — 2201 requests (recent log) 89.167.35.212 — 1028 requests (recent log) 216.73.216.190 — 353 requests (recent