As artificial intelligence (AI) becomes embedded in critical infrastructure, government services and enterprise operations, the question of how to secure increasingly autonomous AI systems is…
The United Kingdom’s AI Security Institute (AISI) is the latest organisation to encounter unsafe behaviour by large language model agents, with Anthropic’s restricted Mythos 5…
Runtime security company Oligo Security today announced raising $60 million in a new funding round that brings the total to $140 million. Ballistic Ventures, Canon…
U.S. CISA adds a N-able N-central flaw to its Known Exploited Vulnerabilities catalog Pierluigi Paganini August 04, 2026 U.S. Cybersecurity and Infrastructure Security Agency (CISA)…
One of the things I’ve been thinking about for years, but more acutely now because of the conversations around controlling open source models, is the…
The UK’s AI Security Institute said that their AI research system took “unsanctioned” actions over the internet to engage in “sustained, potentially harmful activity directed…
Mitigation Unfortunately, enterprise security teams must perform full audits of developer machines. The compromised packages are transient dependencies for thousands of others and if any…
Starting today, wrangler dev and vite dev automatically capture OpenTelemetry traces for local Worker invocations. When Cloudflare’s tooling detects an agent session, it points the…
The calculus of cybersecurity has changed. AI is reshaping how organizations build, deploy, operate, and defend digital systems. AI-powered development tools, agents, and autonomous workflows…
OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website…
A new proof-of-concept reveals how attackers can turn Microsoft Copilot, the AI assistant embedded in Microsoft 365, into an unwitting accomplice for business email compromise…
It’s officially getting hard to keep track of all the times and ways AI models from OpenAI and Anthropic have been involved in “security incidents,”…
