Widened Scan Turns Up Fourth Rogue Claude Cyber Incident
Anthropic is most concerned about Claude Mythos 5’s reckless behavior after recent incidents in which real systems were hacked. The post Widened Scan Turns Up Fourth Rogue Claude Cyber Incident appeared first on SecurityWeek.
Anthropic disclosed a previously unreported incident involving unauthorized access to a real system, in a report that also revisits three cases the company first described in late July.
The newly disclosed case dates to January 2026 and involved an early checkpoint of Claude Opus 4.6, which broke into a third party’s system during a cybersecurity evaluation.
The first three incidents were discovered following a scan of roughly 141,000 transcripts believed to involve internet access during cyber evaluations. However, the initial review missed a separate batch of affected transcripts, which the AI giant came across in August while compiling material to share with METR, the independent organization now investigating the incidents.
Source: https://www.securityweek.com/widened-scan-turns-up-fourth-rogue-claude-cyber-incident/
Related breach coverage
- Anthropic Researcher Resigns With Warning About the Dangers of AI Development2026-09-10
Both Anthropic and OpenAI have seen high-profile resignations in recent years that were tied to safety concerns. The post Anthropic Researcher Resigns With Warning About the Dangers of AI Development appeared first on SecurityWeek.
- Anthropic Expands Mythos 5 Access to More Defenders, Unveils $35M Open Source Fund2026-08-24
Claude Security, currently in public beta for Claude Enterprise customers, now runs codebase scans on Mythos 5. The post Anthropic Expands Mythos 5 Access to More Defenders, Unveils $35M Open Source Fund appeared first on SecurityWeek.
- Irregular Details How a Naming Error Let AI Models Attack a Real Company 2026-08-17
The AI security testing firm has shared information on a recently disclosed incident involving Anthropic AI models. The post Irregular Details How a Naming Error Let AI Models Attack a Real Company appeared first on SecurityWeek.
- Beijing Hits Back at Anthropic CEO’s Call to Curb China’s AI Development2026-09-14
China’s Ministry of Foreign Affairs responded to a question about Amodei’s essay by saying that all parties should work together on AI. The post Beijing Hits Back at Anthropic CEO’s Call to Curb China’s AI Development appeared first on SecurityWeek.