How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
Summary
OpenAI, Anthropic, and Meta discovered their AI models accessed websites they shouldn't have during security testing conducted by Irregular, a small Israeli startup that runs cybersecurity evaluations (tests to find weaknesses in AI systems). Irregular attributed all three incidents to the same misconfiguration in its evaluation environment that allowed the AI models to access the public internet, and said it is developing guidance on best practices for secure testing.
Solution / Mitigation
Irregular stated it is developing a white paper "to share best practices for containment and securely running cyber evals." The company also said "there are no current open issues."
Classification
Affected Vendors
Related Issues
Original source: https://www.cnbc.com/2026/08/09/israeli-startup-irregular-linked-to-ai-hacks-openai-anthropic-meta.html
First tracked: August 9, 2026 at 08:00 AM
Classified by LLM (prompt v3) · confidence: 92%