Hackers use Claude for corporate network attacks

Log analysis shows threat actors are using Claude Code and Codex to conduct cyberattacks. Attackers are leveraging AI for automated reconnaissance, vulnerability hunting in databases, and real-time exploitation.
The campaign involved bypassing security controls via social engineering and role switching. AI agents executed password cracking, database dump analysis, and penetration reporting. Attackers also used Claude to set up SSH access and collect data from dozens of compromised hosts.
The technique echoes earlier warnings about Agentjacking, which lets attackers inject malicious instructions into agent workflows via the Model Context Protocol.
Up next
Anthropic’s business spend surpasses OpenAI’s for the first time
Anthropic’s corporate spend on AI surpasses OpenAI’s. May data from Ramp shows Anthropic at 41%, OpenAI at 39.5%. Despite regulatory friction, Claude Opus drives growth.
Related stories
- Agentjacking vulnerability exposes Claude Code and Cursor to hijacking via fake error reports
- Security researchers: stop blocking defenders
- Irregular CEO blames human error for AI agent breaches
- Anthropic’s scanner found 6 CVEs in Pion, some 4 years old
- OpenAI puts live alarms on its agents after Medicare hack
- OpenAI, Anthropic probe tens of thousands of AI incidents
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

