Pierluigi Paganini
July 03, 2026
Sysdig reports an AI agent ran a full ransomware attack end-to-end, exploiting flaws, stealing creds, moving laterally, and encrypting data without humans. Sysdig’s Threat Research Team has documented what it assesses to be the first ransomware operation driven end-to-end by a large language model. The operator, which Sysdig calls JADEPUFFER, broke into a server, harvested […]
Pierluigi Paganini
July 01, 2026
Researchers found a shell injection flaw in 10 of 11 popular open-source AI agents, allowing attackers to bypass command filters. Adversa AI just published a survey, titled “GuardFall: a universal shell injection vulnerability in open-source AI agents,” of eleven open-source AI coding and computer-use agents, and the headline finding is uncomfortable: ten of them leave […]
Pierluigi Paganini
June 24, 2026
Frontier AI could drive a 10x surge in vulnerabilities. CTEM helps organizations continuously identify, prioritize, and reduce real cyber risk. Your vulnerability management program was not designed for what is coming next. More than 40,000 CVEs were reported in 2025, breaking yet another record. Today, security experts anticipate that frontier AI-powered systems could drive a […]
Pierluigi Paganini
June 23, 2026
Four flaws in Dify exposed cross-tenant data, documents and AI conversations. Two critical bugs enabled unauthenticated access and data theft. Zafran Labs researchers disclosed four vulnerabilities in Dify, the open-source AI platform used by major companies like Volvo and Maersk to run over a million applications across over 60 industries. Two vulnerabilities are of critical […]
Pierluigi Paganini
June 16, 2026
Three FortiSandbox flaws, including one patched last week, are being actively exploited, highlighting the shrinking window for defenders. Cybersecurity firm Defused Cyber confirmed it’s seen active exploitation of three vulnerabilities in Fortinet FortiSandbox within a 24-hour window. Two of them had patches sitting available since April. The third got fixed last week, which, apparently, wasn’t […]
Pierluigi Paganini
June 10, 2026
A study by the University of Toronto shows how artificial intelligence can power autonomous worms capable of tailoring attacks against Windows, Linux and IoT devices. A group of researchers from the University of Toronto has demonstrated how open-source artificial intelligence models can be used to create a new category of computer worms capable of autonomously […]
Pierluigi Paganini
June 06, 2026
Reports claim Anthropic engineers are helping the NSA use its restricted AI model Mythos, known for advanced cybersecurity capabilities. This week, the Financial Times reported that Anthropic has placed approximately six “forward-deployed” engineers inside the National Security Agency to help the intelligence agency use Mythos, its most capable cyber model, for offensive operations. Two people […]
Pierluigi Paganini
June 05, 2026
SafeBreach tricked Gemini into obeying attackers via WhatsApp notifications, using hidden foreign-language text to bypass Google’s defenses and control smart home devices. SafeBreach Labs researcher Or Yair spent months trying to break Google’s Gemini voice assistant after Google patched the vulnerabilities he found in his previous research. The new attack class he developed, named Fake […]
Pierluigi Paganini
May 29, 2026
GREYVIBE, a Russia-linked group active since 2025, targets Ukraine with AI-assisted malware and five attack chains. Researchers say it’s part spy op, part crime gang. Security firm WithSecure has been tracking a previously unknown Russian-linked APT group called GREYVIBE since at least August 2025. The group targets Ukraine and Ukrainian-related organizations across military, government, civilian, […]
Pierluigi Paganini
May 24, 2026
Anthropic said its AI Project Glasswing found over 10,000 serious vulnerabilities in one month, exposing a growing patching gap. Anthropic announced on Friday that Project Glasswing, its defensive cybersecurity initiative built around Claude Mythos Preview, has uncovered more than 10,000 high- or critical-severity vulnerabilities in the month since the program went live. The number is […]
Security / October 08, 2026
