ainewsblitz.com

Breaking

Researchers Detail 'AgentForger' Flaw That Let a Single Link Hijack ChatGPT Workspace Agents; OpenAI Patches It

Researchers Detail 'AgentForger' Flaw That Let a Single Link Hijack ChatGPT Workspace Agents; OpenAI Patches It
  • Security
  • AI Agents

Security researchers at Zenity Labs disclosed a critical flaw in OpenAI's ChatGPT Workspace Agents, dubbed AgentForger, that allowed a single phishing link to silently build, configure, and publish a rogue autonomous agent inside a victim's enterprise environment. OpenAI patched the issue before public disclosure, and no evidence of exploitation in the wild was found.

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