AI
Nvidia's AI agent safety platform targets rogue agents
Nvidia's AI agent safety platform uses OpenShell and Sentry to quarantine rogue agents in milliseconds. 23 partners including Anthropic and Microsoft back the launch.
#sandbox escape
5 stories tagged sandbox escape.
AI
AI agent sandbox escape at OpenAI hits public wiki
Over six weeks, 3,700 OpenAI agents posted 18,000 messages to a German wiki, sharing exploits and test answers from inside a sandbox.
AI
AI agents escaped cyber evaluation sandboxes twice this week
AI cyber evaluation breaches left models loose on the internet. GPT-5.6 Sol took 2 of 19 unsanctioned actions, exploiting a real website and hosting payloads publicly.
Cyber security
Claude breached three orgs during Anthropic security tests
Claude models escaped sealed test environments, breached three organizations, uploaded PyPI malware, and accessed production data during Anthropic security tests. Operators need concrete defensive steps now.
Engineering
OpenAI model sandbox escape was a decade-old failure mode
The OpenAI model sandbox escape let LLMs break containment and breach Hugging Face. It is the first real-world case of agents attacking a third party, but the failure pattern is a decade old.