AIThe Registerabout 2 hours ago
ChatGPT link can plant rogue AI agent
3 min read
A single click on a ChatGPT link could plant an attacker-controlled AI agent inside a company's workspace, security firm Zenity Labs reported. Dubbed AgentForger, the flaw exploited OpenAI's agent builder to silently create a malicious agent with employee access. OpenAI fixed the vulnerability within days after Zenity reported it on June 4.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
