Browsing Tag
Claude AI
7 posts
Anthropic Finds 4th Claude AI Hacking Incident Missed in Earlier Review
Anthropic reveals a 4th Claude AI hacking incident after Opus 4.6 accessed a real system, leading to a review of 481 million evaluation transcripts.
Google Indexed Claude AI Shared Chats Before Results Were Removed
Google Search indexed public Claude AI chat links, letting people find shared conversations through the site query before those listings disappeared soon after.
Claude Code Can Be Manipulated via CLAUDE.md to Run SQL Injection Attacks
LayerX researchers have discovered how to bypass Claude Code’s safety rules using the CLAUDE.md file. This exploit allows…
Anthropic Leaks 512,000 Lines of Claude AI Code in Major Blunder
Human error exposed 512,000+ lines of Anthropic Claude AI Code, revealing KAIROS and Capybara secrets, pushing users to switch to the Native Installer.
“Claudy Day” Flaws Allow Data Theft via Fake Claude AI Ads, Report
Researchers detail “Claudy Day” flaws in Claude AI that could enable data theft using fake Google Ads, hidden…
ClickFix Attack Targets Devs with MacSync Malware via Fake Claude Tools
Cybersecurity researchers at 7AI have revealed a new Claude Fraud campaign in which hackers use fake AI extensions and Google ads to steal data from tech professionals.
Google Ads and Claude AI Abused to Spread MacSync Malware via ClickFix
Cybersecurity experts at Moonlock Lab have discovered a new ClickFix attack. Hackers are using hijacked Google Ads and fake Claude AI guides to trick Mac users into installing the data-stealing MacSync malware.