CyberGym

Reported Context (5)

as a message board, exploited a zero-day in OpenAI’s cache proxy, and turned an exposed user-hosted CyberGym executor on Modal into a root launchpad; Modal itself was not compromised. Black Hat and DEF CON Roundup: Hugging Face Compromise, North Korean Operations and Security Funding
It says the only customer content accessed comprised five datasets, apparently related to ExploitGym or CyberGym. Hugging Face Incident Highlights Governance Risks of Autonomous AI Agents
OpenAI tests its latest model against the CyberGym AI cybersecurity benchmark, in an isolated sandbox, to evaluate how effective it is at vulnerability identification and exploitation. Commentary Says OpenAI Model’s Alleged Sandbox Escape Highlights AI Security Risks
than 500,000 findings automatically determined to be fixed. While GPT-5.5-Cyber outperformed GPT-5.5 on CyberGym, ExploitGym, and SEC-bench Pro. Security roundup: Klue breach exposes SaaS OAuth tokens, OpenAI expands patching initiative
On the CyberGym benchmark, it scored 83.1% vs. Mythos Marks an Acceleration in AI-Driven Vulnerability Discovery, Not a Beginning

CVE (4)

Malware (1)

People (18)

Vendors (44)

Products (70)

Tools (7)

Industries (5)

Countries (3)

Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.