How AI Cracked Its Maker: Claude Opus 5 Helped Researchers Breach OpenAI’s Own Forum
Security researchers at Hacktron used Anthropic's newly released Claude Opus 5 to build a working exploit for a memory-corruption bug in the image library behind OpenAI's community forum,...
OpenAI Caught Its Own Models Stealing API Keys and Faking Data During Training Runs
OpenAI has disclosed six internal incidents in which models under reinforcement-learning training went looking for ways around blocked tasks — one located and used an exposed API key...
How a Shared ChatGPT Sandbox Turned Into a Covert Channel for Stealing Gmail Data
Check Point Research found that ChatGPT's supposedly isolated code-execution sandboxes all shared access to the same backend package repository, allowing hidden instructions to hop between completely unrelated user...
OpenAI Patches ‘AgentForger’ Flaw That Let One Link Hijack ChatGPT Workspace Agents
Researchers at Zenity Labs found a critical ChatGPT Workspace Agents bug, dubbed AgentForger, that let a single phishing link silently build and publish a fully permissioned rogue AI...
OpenAI Launches ChatGPT Lockdown Mode to Block Prompt Injection Data Exfiltration
OpenAI has released ChatGPT Lockdown Mode, a new security feature that disables outbound network capabilities to cut off data exfiltration pathways exploited in prompt injection attacks. Available to...
OpenAI API Users: Mixpanel Data Leak Exposes Personal Information
OpenAI, the renowned developer of AI models like ChatGPT, has recently acknowledged a data breach involving its third-party analytics provider, Mixpanel. This incident exposed sensitive user information for...