ainewsblitz.com

Breaking

Researchers Disclose 'AgentForger' Flaw That Let a Single ChatGPT Link Plant a Rogue AI Agent

Researchers Disclose 'AgentForger' Flaw That Let a Single ChatGPT Link Plant a Rogue AI Agent
  • Security
  • AI Agents

A single crafted link on chatgpt.com could have silently created, configured, and scheduled a rogue autonomous AI agent inside a company's workspace, security researchers say. The flaw, dubbed AgentForger, was found by Zenity Labs in OpenAI's ChatGPT Workspace Agents feature and was fixed by OpenAI within days of being reported.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year