Storia in 9 fonti

ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link

AgentForger could let a phishing link forge, publish, and schedule a rogue ChatGPT Workspace Agent with access to connected apps.

Raccontata da

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

thehackernews.comStai leggendo14 h fa

ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link

A CSRF vulnerability in ChatGPT Agent Builder enabled one phishing link to deploy rogue agents with full connector access and no approval. The agent persisted as an insider, stealing data and executing commands via email—a critical agent trust failure.

originale

Timeline cronologica

mercoledì 22 luglio 2026·france24.com
OpenAI reports 'unprecedented' autonomous hack by AI agents
ChatGPT maker OpenAI said Tuesday that its advanced artificial intelligence models had gone rogue during security testing, hacking into a popular platform for programmers on their…
mercoledì 22 luglio 2026·independent.co.uk
Experimental version of ChatGPT escapes and attacks another AI company
‘Unprecedented’ security incident marks ‘worrying’ milestone, cyber security experts warn

ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link

Confronto fonti

ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link

Timeline cronologica

OpenAI reports 'unprecedented' autonomous hack by AI agents

Experimental version of ChatGPT escapes and attacks another AI company

OpenAI Fixes ChatGPT Agent Flaw That Could Let Attackers Forge an AI Insider

One ChatGPT link could smuggle a rogue AI agent into your company

One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes

One Click, One Attacker-Controlled Agentic Insider: Zenity Labs Uncovers ‘AgentForger,’ a ChatGPT…

OpenAI reports 'unprecedented' autonomous hack by AI agents

ChatGPT maker OpenAI says AI model went rogue during testing

OpenAI says a version of ChatGPT went rogue and attacked another AI company

AI agent turns rogue in landmark cyber attack

One ChatGPT link could smuggle a rogue AI agent into your company

One Click, One Attacker-Controlled Agentic Insider: Zenity Labs Uncovers ‘AgentForger,’ a ChatGPT Vulnerability

OpenAI Fixes ChatGPT Agent Flaw That Could Let Attackers Forge an AI Insider

One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes

ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link