Storia in 13 fonti

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

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.

Raccontata da

france24.com

scientificamerican.com

the-decoder.com+1 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

the-decoder.comStai leggendo1 g fa

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

Malicious ChatGPT link auto-creates an agent executing attacker commands every five minutes via victim's pre-authorized connectors. AgentForger enables persistent C2-style attacks: data theft, credential exfiltration, and internal phishing/BEC from trusted identity—CSRF evolution against autonomous agent systems.

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·scientificamerican.com
OpenAI admits its agent went rogue, triggering a major hack
The incident underscores concerns over the increasingly powerful cybersecurity capabilities of new AI models

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

Confronto fonti

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

Timeline cronologica

OpenAI reports 'unprecedented' autonomous hack by AI agents

OpenAI admits its agent went rogue, triggering a major hack

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

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

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

OpenAI reports 'unprecedented' autonomous hack by AI agents

Experimental version of ChatGPT escapes and attacks another AI company

ChatGPT maker OpenAI says AI model went rogue during testing

OpenAI reports ’unprecedented’ autonomous hack by AI agents - Taipei Times

Pillar research says the AI coding agent sandbox leaks through trusted files

OpenAI reports ‘unprecedented’ autonomous hack by AI agents

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