Storia in 10 fonti

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

Raccontata da

france24.com

scientificamerican.com

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

morningstar.comStai leggendo1 mese fa

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

Zenity Labs scoprì AgentForger: vulnerabilità in ChatGPT Agents che via phishing link creava agente autonomo con identità legittima della vittima e accessi aziendali. AgentForger rappresenta una nuova classe di attacchi: insider agentico persistente, non furto di sessioni; controlli di sicurezza tradizionali non monitorano agenti autonomi.

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

Confronto fonti

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

Timeline cronologica

OpenAI reports 'unprecedented' autonomous hack by AI agents

OpenAI admits its agent went rogue, triggering a major hack

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

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

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

OpenAI reports 'unprecedented' autonomous hack by AI agents

OpenAI says its models went rogue and hacked startup in ‘unprecedented incident’

Experimental version of ChatGPT escapes and attacks another AI company

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