CVEs, exploits, and security flaws in AI frameworks, models, and infrastructure.
A critical flaw in Hugging Face Transformers lets attackers execute arbitrary code on anyone who loads a poisoned model, silently bypassing the trust_remote_code=False safety flag. 232 million vulnerable downloads preceded the March patch.
Varonis Threat Labs chained three bugs in Microsoft 365 Copilot Enterprise Search to build a one-click exfiltration path that pulls emails, files, and live MFA codes without any OAuth prompt or user consent beyond clicking a Microsoft-domain URL.
Two critical CVEs in Microsoft Semantic Kernel let attackers chain prompt injection into arbitrary file writes and code execution. Patch to .NET SDK 1.71.0 and Python SDK 1.39.4 immediately.
Check Point Research found three CVEs in LangGraph's persistence layer. CVE-2025-67644 SQLi chains with CVE-2026-28277 deserialization to reach RCE.
Adversa AI disclosed SymJack (symlink hijacking to plant malicious MCP servers) and TrustFall (trust dialog bypass) hitting six AI coding agents including Copilot and Cursor.