PromptSnatcher (internal identifier: Panel 231) is a modern, stealthy data collection operation embedded inside two browser extensions that masquerade as ad‑blockers while harvesting full chat conversations and account metadata from major AI platforms….

Anthropic’s latest AI release, Claude Fable 5, is facing scrutiny after claims emerged that researchers have successfully jailbroken the model to generate sensitive and potentially harmful outputs, including guidance relevant to exploit development and…

Malicious browser add-ons are actively harvesting conversations and personal data from users of major AI platforms including ChatGPT, Claude, Copilot, Gemini, and DeepSeek. The threat leverages ostensibly helpful Chrome extensions VPNs, sidebars, and “…

Taxonomy of Failure Modes in Agentic AI Systems v2.0 published in April 2026, the field received more than a classification update: it got operational guidance grounded in a year of real-world red teaming that exposed how quickly agentic AI systems tra…

A threat campaign in which attackers leveraged AI-powered tools to streamline Active Directory (AD) compromise and accelerate endpoint detection and response (EDR) evasion testing. The activity, observed on June 2, 2026, was triggered by suspicious fil…

Anthropic has expanded its Project Glasswing initiative, significantly scaling access to its Claude Mythos Preview model as part of a broader effort to strengthen global software security. The program, first launched in April 2026 with around 50 organi…