Product
vLLM
- First Reported
- Sep 30, 2025
- Latest Reported
- Oct 20, 2026
Reported Context (9)
- vLLM, a widely adopted open-source LLM inference engine, disclosed seven critical and high-severity vulnerabilities in 2025–2026—including remote code execution via unsafe deserialization (CVE-2025-47277, CVSS 9.8) and GreyNoise Report Highlights Edge Targeting, Fresh Attack Infrastructure and LLM Scanning
- vLLM Multimodal Heap-Address Information Leak Scanner Metasploit Update Adds Exploit Modules, Windows AArch64 Payloads and Enhancements
- vulnerability in LMCache, open-source software that speeds up large language model (LLM) servers such as vLLM, lets an attacker run code on the cache server without logging in, and no fixed version is available. Critical LMCache Flaw Enables Unauthenticated Remote Code Execution
- The report highlights rapid abuse of an AI-discovered issue in BeyondTrust Privileged Remote Access and Remote Support, along with growing targeting of AI software such as Flowise, Langflow, vLLM, Ollama, and LiteLLM. GTIG Finds Attackers Quickly Exploited an AI-Discovered BeyondTrust Flaw
- vLLM, Ollama, LiteLLM, Llama.cpp, Triton (NVIDIA), Ray, TGI, SGLang, TensorRT-LLM, BentoML, LocalAI Google Finds AI Is Changing Vulnerability Discovery and Exploitation Trends
CVE (24)
Malware (3)
People (20)
Threat Actors (2)
MITRE ATT&CK (6)
Vendors (20)
Products (46)
Tools (6)
Industries (1)
Countries (4)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
