AI Recommendation Poisoning: How ‘Ask AI’ Buttons Silently Alter LLM Memory
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
Latest cybersecurity news, breaches, vulnerability disclosures and industry developments.
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
Attackers breached an organization's Oracle database via a SQL injection flaw in a public-facing web application, then installed a post-exploitation toolkit named…
A federal judge in Alexandria, Virginia, sentenced Maksim Silnikau, a 40-year-old Belarusian national, to 16 years in prison on August 5, 2026,…
Connor Riley Moucka, a 26-year-old Canadian national, pleaded guilty in Seattle federal court to computer fraud, wire fraud, aggravated identity theft, and…
OpenAI has disrupted a Cambodia-based scam operation that leveraged its ChatGPT AI chatbot to facilitate a wide range of fraudulent schemes, including…
Cybersecurity researchers at Okta have uncovered a network of underground services selling discounted access to Anthropic's large language models (LLMs), including Opus…
Kali365, a device code phishing kit, is actively targeting US organizations by abusing Microsoft's legitimate authentication flow. According to ANY.RUN telemetry, the…
GitGuardian researchers have uncovered a significant security risk affecting n8n, a popular open-source workflow automation platform. By scanning public GitHub commits, they…
A cluster of 77 malicious extensions on the Open VSX marketplace has been discovered impersonating legitimate developer tools while exfiltrating sensitive information…