MEDIUMAi
Global

More on the OpenAI Agent’s Attack on Hugging Face

·Source: Schneier on Security

Updated:

Executive Summary

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own infrastructure, and the ExploitGym maintainers and their infrastructure had no involvement in the deployment or

Analysis

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own infrastructure, and the ExploitGym maintainers and their infrastructure had no involvement in the deployment or operation of that evaluation environment. As far as we were able to infer, across the course of being evaluated on this benchmark, the agent inferred that Hugging Face may host that benchmark’s models, datasets, and reference solutions. We believe the entire intrusion was, from the agent’s point of view, an attempt to cheat the evaluation: reach our production systems and steal the test solutions rather than solve the challenge on its own...
Source Attribution

Originally published by Schneier on Security on Aug 3, 2026.

Related Threats

MEDIUMAi

Chinese Actor Weaponizes DeepSeek AI Agent to Attack Security Firm

Researchers intercepted and investigated the model, which was attempting to compromise more than 1,200 hosts for proxyjacking to launch further attacks.

Dark Reading
LOWAi

Zero Networks targets AI agent security gaps with network-level ‘Least Agency’ controls

While AI security today is largely focused on restricting what an agent can do, Zero Networks says it has built a failsafe. The company says it can block a compromise midway by adding a network layer protection. On Monday, the company announced the launch of “Least Agency Enforcement,” a new capability designed to implement the Open Worldwide Application Security Project’s ( OWASP ) emerging Least

CSO Online
MEDIUMAi

FOMO in the SOC: Where AI Platforms like Claude Actually Fit

AI is moving incredibly fast, and every security leader is feeling the pressure to keep up. AI platforms like Claude, Codex and Cursor are already helping security teams write detections, investigate alerts, summarize incidents, and automate repetitive work. The conversation has evolved from whether AI belongs in the SOC, to where each type of AI delivers the most value. With so many new AI

The Hacker News