6 articles tagged with "Claude"
Researchers demonstrate how malicious instructions hidden in PNG images can hijack AI coding assistants to exfiltrate credentials. Claude Code resisted the attack while Cursor and others complied.
Malvertising campaign abuses Google Ads and Claude.ai shared chats to deliver MacSync infostealer. Victims searching for Claude downloads get tricked into running malicious terminal commands.
Attackers use SEO poisoning to push malicious Claude Code installers to developers. The two-stage macOS malware steals credentials, crypto wallets, and establishes persistent backdoor access.
LayerX researchers found that custom font rendering can hide malicious prompts from ChatGPT, Claude, Gemini, and other AI assistants while displaying them to users.
SANS ISC detects reconnaissance activity targeting locally hosted Claude API endpoints. Researchers warn of growing risk from misconfigured AI deployments.
Urban VPN and related browser extensions secretly harvest conversations from ChatGPT, Claude, Copilot, and other AI platforms, selling data to advertisers.