vllm vulnerabilities

Browse known CVEs and advisories by package and ecosystem. Severity tells you the worst case. What determines real risk is whether the vulnerable code actually runs in your applications.

Browse by ecosystem

npm PyPI Maven Go RubyGems Cargo NuGet Composer pub Swift GitHub Actions

CVE-IDSeverityPackage summary

GHSA-GGPF-24JW-3FCWCriticalvllm: CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0 GHSA-HF3C-WXG2-49Q9Mediumvllm: vLLM vulnerable to Denial of Service by abusing xgrammar cache CVE-2024-9053Criticalvllm: vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints CVE-2024-9052Criticalvllm: vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object CVE-2024-11041Criticalvllm: vLLM Deserialization of Untrusted Data vulnerability CVE-2025-29783Criticalvllm: vLLM Allows Remote Code Execution via Mooncake Integration CVE-2025-29770Mediumvllm: vLLM denial of service via outlines unbounded cache on disk CVE-2025-25183Lowvllm: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache CVE-2025-24357Highvllm: vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator CVE-2024-8768Highvllm: vLLM denial of service vulnerability CVE-2024-8939Mediumvllm: vLLM Denial of Service via the best_of parameter

Stop the waste.
Protect your environment with Kodem.

Get a personalized demo

Get a personalized demo