AI News HubLIVE
站内改写

Attackers abuse shared ChatGPT and Claude chats to spread malware

Attackers are exploiting the chat-sharing features in ChatGPT and Claude to spread malware through shared conversations. The chats mimic error messages or install guides and slip past security tools undetected because they're hosted on trusted domains.

Article intelligence

EngineersIntermediate

Key points

  • Attackers exploit ChatGPT and Claude chat-sharing to host malicious content.
  • Shared chats are disguised as error messages or installation guides.
  • Trusted domains help malicious links evade security tools.

Why it matters

This matters because attackers exploit ChatGPT and Claude chat-sharing to host malicious content.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

Attackers are exploiting the chat-sharing features in ChatGPT and Claude to spread malware through shared conversations. The chats mimic error messages or install guides and slip past security tools undetected because they're hosted on trusted domains.

The article Attackers abuse shared ChatGPT and Claude chats to spread malware appeared first on The Decoder.