Article Machine Learning Robotics

Hugging Face LeRobot CVE-2026-25874: Unauthenticated Pickle RCE Over gRPC, Still Unpatched

A critical pre-authentication remote code execution vulnerability has been disclosed in LeRobot, Hugging Face's open-source robotics framework with nearly 24,000 GitHub stars.

Article SSRF LLM Security

LMDeploy SSRF (CVE-2026-33626) Weaponized Within 13 Hours of Disclosure — Your AI Inference Box Is a Metadata-API Probe

Between the moment GitHub published advisory GHSA-6w67-hwm5-92mq — later assigned CVE-2026-33626 — and the first in-the-wild exploitation attempt, 12 hours and 31 minutes passed.

Article Prompt Injection IDE Security

Google Antigravity IDE: Prompt Injection Through find_by_name Turns File Search Into Full RCE

Researchers at Pillar Security have disclosed a vulnerability in Google's agentic IDE, Antigravity, that lets an attacker escalate a simple prompt injection into full remote code execution — bypassing the IDE's most…

Article Remote Code Execution MLOps

SGLang CVE-2026-5760: A Malicious AI Model File Is Enough to Get RCE on Your Inference Server

A critical unpatched vulnerability in SGLang — a popular high-performance AI serving framework — lets an attacker execute arbitrary code on the server simply by convincing it to load a malicious GGUF model file.

Article MCP Supply Chain

Anthropic's MCP Has a By-Design RCE Flaw Affecting 200,000 Servers — and Anthropic Won't Fix It

Researchers at OX Security have published a systemic vulnerability in the Model Context Protocol (MCP), Anthropic's open standard for connecting AI assistants to external tools and data.