Cisco Talos found hackers using simple authorization claims to bypass AI guardrails, build DDoS attack tools, steal credentials and access live camera services.

Hackers are using fake Claude Code guide and AI PDFs to spread AsyncRAT malware via Windows attack using PowerShell and Defender exclusions.

Fake Anthropic websites are being used to target Claude Code users with a fileless infostealer campaign that steals browser credentials and evades detection.

Researchers at Ontinue have discovered an undocumented malware campaign targeting developers with fake Claude Code installers to steal browser passwords and cookies.

Cybersecurity researchers at Forcepoint uncover new indirect prompt injection attacks that use hidden website code to exploit AI assistants like GitHub Copilot.