Meta, Nvidia, Microsoft AI Frameworks Exposed to Critical Flaws

Copy-paste vulnerability hits AI inference frameworks at Meta, Nvidia, and Microsoft

Cybersecurity researchers have uncovered a chain of critical remote code execution (RCE) vulnerabilities in major AI inference server frameworks, including those from Meta, Nvidia, Microsoft, and open-source projects such as vLLM and SGLang. According to Oligo Security, these vulnerabilities stand out for the way they propagated. Developers copied code containing insecure patterns across projects, effectively transplanting the same flaw into mul…

AI’s Achilles Heel: Critical Bugs Plague Inference Engines in 2025

In the rapidly evolving landscape of artificial intelligence, where inference frameworks power everything from chatbots to autonomous systems, a new wave of vulnerabilities has emerged, threatening the very foundations of AI deployment. Cybersecurity researchers have recently uncovered severe remote code execution flaws in popular AI inference engines from tech giants Meta, Nvidia, and Microsoft. These discoveries, detailed in a report by The Ha…

ShadowMQ Flaw Exposes AI Inference Engines to Remote Code Execution

Oligo Security researchers found a repeating, unsafe pattern in several AI inference frameworks that can allow remote code execution when unauthenticated ZeroMQ sockets deserialize Python objects. Introduction to Malwa…

MCP Hijacking of Cursor’s New Browser

Discover how a malicious MCP server can hijack Cursor’s internal browser, steal credentials, and compromise developer machines.

Researchers Find Serious AI Bugs Exposing Meta, Nvidia, And Microsoft Inference Frameworks - Cybernoz - Cybersecurity News

Cybersecurity researchers have uncovered critical remote code execution vulnerabilities impacting major artificial intelligence (AI) inference engines, including those from Meta, Nvidia, Microsoft, and open-source PyTorch projects such as vLLM and SGLang. “These vulnerabilities all traced back to the same root cause: the overlooked unsafe use of ZeroMQ (ZMQ) and Python’s pickle deserialization,” Oligo Security researcher Avi Lumelsky said in a r…

Researchers Find Serious AI Bugs Exposing Meta, Nvidia, and Microsoft Inference Frameworks

Cybersecurity researchers have uncovered critical remote code execution vulnerabilities impacting major artificial intelligence (AI) inference engines, including those from Meta, Nvidia, Microsoft, and open-source PyTorch projects such as vLLM and SGLang. "These vulnerabilities all traced back to the same root cause: the overlooked unsafe use of ZeroMQ (ZMQ) and Python's pickle deserialization,"