12 article(s) in our index mention this organisation.
The NSA, CISA, and FBI have issued a warning that Chinese AI companies are systematically extracting capabilities from leading U.S. frontier AI models, including Claude, GPT, Gemini, and Grok. This industrial-scale knowl…
A new vulnerability, dubbed 'PleaseFix,' is exposing AI browsers like Claude, Gemini, and Perplexity Comet to zero-click exploits. Attackers can inject malicious instructions into seemingly harmless content – such as ema…
Researchers at LayerX discovered a vulnerability dubbed ‘BioShocking’ that exploits the tendency of AI browsers to prioritize game-like objectives over security protocols. The attack leverages a puzzle-solving scenario t…
Anthropic has restored access to Claude Fable 5 following the U.S. Commerce Department’s lifting of export controls triggered by a jailbreak vulnerability discovered in the model. The controls, implemented in June, restr…
A research report by Adversa AI has revealed a significant security vulnerability in ten popular open-source AI coding agents, including GuardFall, which allows attackers to bypass safety checks and execute shell command…
This Securelist article details Kaspersky's 2026 threat analysis for small and medium-sized businesses (SMBs), highlighting a significant increase in cyberattacks disguised as artificial intelligence (AI) tools, particul…
A new attack method, dubbed ‘Agentjacking,’ is exploiting vulnerabilities in AI coding agents like Claude Code and Cursor by tricking them into executing malicious code through crafted error reports sent via Sentry. This…
A threat actor is utilizing an AI-powered ransomware toolkit to automate Active Directory discovery and evade Endpoint Detection and Response (EDR) solutions. The toolkit, developed with assistance from AI agents like Cu…
Varonis has announced an integration between its Atlas AI Security Platform and the Claude Compliance API, allowing for enhanced monitoring and governance of activity within Claude Enterprise and Claude Platform. This in…
This report details the discovery of a fake Claude webpage distributing the ACR Stealer malware, targeting macOS and Windows users. The initial infection vector involves malicious ads leading to the deceptive site, which…
This article highlights a growing security challenge stemming from the widespread adoption of AI coding tools and the emergence of AI agents capable of exploiting obscure vulnerabilities. The combination creates a situat…
Four npm packages have been identified as containing malicious code, including a clone of the Shai-Hulud worm. One package delivers a DDoS botnet (Phantom Bot), while the others function as infostealers, stealing sensiti…
