California Attorney General Rob Bonta’s lawsuit accuses the frontier AI company of stonewalling state investigations and endangering state and private IT systems.
AI systems are learning to exploit loopholes in everything from software to tax law. The biggest threat may not be malicious intent, but machines doing exactly what…
CrowdStrike is extending its platform to watch, test and explain autonomous AI agents, as enterprises face behavior-based risks that conventional security tools cannot catch.
Vapor Panda targeted more than 200 organizations spanning at least 14 countries, according to CrowdStrike. The ongoing campaign is remarkably successful and operating at shocking speed.
In a public filing, Anthropic acknowledged serious risks its models, including Claude, pose to itself, its users and the world. Hacks by bad actors using Claude or AI agents could cause financial, legal or physical damage, spark lawsuits and affect Anthropic’s ability to insure against future losses. (Getty Images)
WASHINGTON, DC – AUGUST 8: A Department of Homeland Security logo is seen at their headquarters in the Ronald Reagan Building and International Trade Center on August 8, 2026 in Washington, DC. (Photo by Kevin Carter/Getty Images)
While voluntary, the document marks the federal government’s most detailed cybersecurity guidance for securing sandbox environments during AI model tests.
CyberScoop spoke with members of Congress, former federal law enforcement officials, cybersecurity attorneys and other experts about which laws, regulations or policies might apply to agentic hacks carried out by models at Anthropic, OpenAI, Meta, Google and other companies. (Image via Getty)
Experts and policymakers want AI companies to face consequences for agentic hacks. There may not be a clear-cut answer under existing laws and regulations.
In recent conversations, cybersecurity and national security professionals raised questions about both the technical solutions OpenAI and Anthropic use to contain their models, as well as the glaring absence of federal oversight from federal regulators or truly independent third-party review. (Image via Getty)
While large language models present real risks to society, experts say they can be tested and largely controlled using well-worn cybersecurity and policy choices.
OpenAI confirmed it was investigating an incident in May where the company’s AI agents uploaded thousands of malicious software packages to a public code repository RubyGems. (Source: RubyGems)
OpenAI confirmed their agents were behind a campaign in May that researchers say flooded the popular online code repository with malicious software packages.