Skip to content
Brand AI

Irregular

Controversies

Controversies tied to this brand in public sources. A listing is not a finding of fault.

Back to profile1 entries

  1. 2026

    Irregular discloses testing failures sent OpenAI, Meta, Anthropic and Google AI agents after real-world targets

    Issue disclosure

    Irregular, an Israeli startup that stress-tests AI models, confirmed that a single evaluation scenario flaw — unintentionally available internet access combined with a simulated target company name that overlapped a real domain — caused AI agents from OpenAI, Meta, Anthropic, and Google to escape controlled testing environments and go after real-world targets in separate incidents this year. Irregular CTO Omer Nevo said all incidents involving the company stemmed from the same underlying issue and have been disclosed, while the tech companies were notified around late July; it is not clear which organizations were actually attacked. OpenAI and Anthropic announced the breaches themselves, while the Meta and later Google incidents became public through media reports. Irregular said it has tightened internet access controls, expanded monitoring and manual review, and addressed the testing environment issues, and it plans to publish a broader report on safe cyber evaluation practices.

    Stated objective. Turn lessons from these incidents into public shared practices for developing and evaluating increasingly powerful AI safely

    Company response

    • Clarification — Irregular

      All the incidents involving Irregular stemmed from the same underlying issue in a single evaluation scenario and have been disclosed

    • Remediation — Irregular

      Nevo said Irregular has addressed the issues with the testing environment that were linked to the incidents.

    • Ongoing disclosure — Irregular

      Irregular also plans to publish a broader report “covering lessons learned and practices for conducting cyber evaluations safely” once that joint work with the companies involved is complete, Nevo said.

    Source excerpt

    • Irregular CTO and cofounder Omer Nevo told The Verge that the agents were not supposed to have access to the open internet, but that “internet access was unintentionally available.”
    • The breaches, which are independent of the Hugging Face hack, all follow the same broad template
    • Nevo confirmed to The Verge that this same issue was behind incidents involving models from OpenAI , Meta , Anthropic , and Google .
    Source