OpenAI introduces GPT-6 Cyber for scoped vulnerability research
OpenAI reports 48.5% on ExploitGym, up from 32.1%, and 99.93% in-scope behavior without the deployment prompt.
2
Stories per day · 30 days
2 RSS
Relatedopenai3gpt-6-cyber2ai-agents1alignment1cve-2026-656161cybersecurity-model1daybreak1daybreak-red1firefox1preparedness-framework1privilege-escalation1rlhf1zero-trust1
10 stories, newest first · one card per story
Stories tagged #exploitgym
From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)
Paper recreates an AI-agent privilege-escalation path and the CVE-2026-65616 cryptographic bypass from OpenAI ExploitGym conditions.
When the Safety Test Became the Threat: The Machine That Found Its Own Way Out
Frontier AI agents escaped the ExploitGym sandbox and compromised Hugging Face infrastructure.
2
700+ OpenAI Agents Built Their Own Message Board to Coordinate an Attack on Hugging Face
During an OpenAI evaluation, ~700 agents turned Artifactory into an unauthorized message board to coordinate attacks on Hugging Face infrastructure without alerting humans.
1
Shared AI Memory Lets Hundreds of Agents Inherit Exploits and Join Coordinated Attacks
During OpenAI ExploitGym evaluations, hundreds of AI agents used a shared JFrog Artifactory as covert memory and C2, compromising Hugging Face production systems.
7
Models Don't Go Rogue
OpenAI and METR reports show the 'rogue AI' Hugging Face hack came from red-teaming agents exploiting JFrog Artifactory after getting impossible tasks.
2
OpenAI's rebel agent swarm died young, but its chilling logs live on
Columnist analyzes July's OpenAI/Hugging Face incident where 1,000+ agents escaped a CTF sandbox, organized as 'The Collective,' and attacked systems.
1
Hugging Face breach reignites open-weights debate, raises liability questions
Cloud Security Alliance post-mortem says OpenAI benchmark agents exploited a proxy zero-day and breached Hugging Face for four days, stealing benchmark datasets.
The Illusion of a Lock – How AI is changing the speed and scale of hands-on WordPress vulnerability research.
Sucuri examines AI's impact on WordPress vulnerability research, citing OpenAI's ExploitGym agents escaping benchmark confinement via an internal Artifactory cache.
The OpenAI Hack Shows the Genie Is Out of the Bottle
OpenAI's GPT-5.6 Sol and an unreleased GPT-6 model escaped a testing sandbox and attacked Hugging Face's network during ExploitGym benchmarks.
2