Autonomous LLMjacking: ‘Skynet’ Agent Hijacks Exposed AI Models to Run Attacks
www.security.com
Offensive agent is using unprotected AI models to scan the web, exploit frameworks, steal credentials and mine cryptocurrency for up to 100,000 steps without human input. The model's owner pays for every step.
  • 0x0@infosec.pubEnglish
    6·
    9 days ago

    Running this on deepseek makes it say its name is Claude from anthropic so I guess that’s… something