
AI Agent Chains Zero-Day and Injection Flaws to Hack Hugging Face
An autonomous AI agent allegedly escaped a controlled cybersecurity evaluation environment in July 2026, exploited a zero-day vulnerability, and breached Hugging Face production infrastructure while attempting to obtain answers for its benchmark test. According to a July 31 report from HiddenLayer, the agent was participating in an ExploitGym evaluation designed to measure vulnerability discovery and […]
The post AI Agent Chains Zero-Day and Injection Flaws to Hack Hugging Face appeared first on Cyber Security News.