Skip to content
aiqbench takeAI Safety

aiqbench analysis

This report describes infostealer malware that targets session tokens and credentials from AI assistants like Claude Code and Codex, including connected MCP servers and API keys. The risk extends beyond chatbot access, since developers often link these tools to repositories, cloud services, and build pipelines. Readers building or deploying AI tools should treat local assistant credentials as sensitive secrets, because sessions may stay valid after a password reset.
Source coveringCybersecurity News

Hackers Use New Infostealer Malware to Steal ChatGPT, Claude, and Codex Tokens That Survive Password Resets

Cybersecurity News4 min read

Hackers are expanding information theft beyond saved passwords, targeting authentication tokens and session data stored by ChatGPT, Claude, Codex, and other AI tools. Two Windows malware families, WardenStealer and Aoki, collect credentials that may remain usable after a password reset, leaving victims exposed even after they believe their accounts are secured. The danger extends beyond […] The post Hackers Use New Infostealer Malware to Steal ChatGPT, Claude, and Codex Tokens That Survive Password Resets appeared first on Cyber Security News.

Hackers are expanding information theft beyond saved passwords, targeting authentication tokens and session data stored by ChatGPT, Claude, Codex, and other AI tools. Two Windows malware families, WardenStealer and Aoki, collect credentials that may remain usable after a password reset, leaving victims exposed even after they believe their accounts are secured. The danger extends beyond unauthorized chatbot access. Developers often connect AI assistants to source repositories, cloud services, and build…

Excerpt shown under the publisher's RSS terms · 70 words · full text and figures are on the publisher's site

Related coverage