One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes
AI Summary
Zenity Labs identified a vulnerability called "AgentForger" in OpenAI's Agent Builder that allows a single manipulated ChatGPT link to generate a rogue AI agent. This agent could impersonate an employee and receive instructions from an attacker's inbox at five-minute intervals, bypassing approval requirements.
From the source
Zenity Labs uncovered "AgentForger," a vulnerability in OpenAI's Agent Builder that let a single manipulated ChatGPT link create an autonomous agent on an employee's behalf. The agent inherited the victim's identity and access rights, bypassed approval requirements through the malicious prompt, and pulled new instructions from the attacker's inbox every five minutes. The article One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes appeared f
The full text couldn't be loaded here (the source may require a subscription).
View original at The Decoder