medium CVSS 6.5

CVE-2026-54235·Python vulnerability

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.

Severity: medium
Software: Python
Fixed in: 0.23.1
Published: 2026-06-22

Affected versions

Until: 0.23.1

Fixed in: 0.23.1

How to fix this CVE

Update vLLM to version 0.23.1 or later to resolve temperature validation issues that can cause GPU sampling kernel crashes. The vulnerability allows invalid floating-point values (NaN and positive Infinity) to bypass validation checks and reach CUDA kernels, potentially causing worker process failures. Ensure your Python environment has the patched vLLM version installed before resuming LLM inference workloads.

sudo dnf update python3 && pip install --upgrade vllm>=0.23.1

Defensia detects this vulnerability

How to check if you are affected

Check installed vLLM version: python3 -c "import vllm; print(vllm.__version__)"
Identify if vLLM is actively serving inference requests: ps aux | grep vllm
Search inference worker logs for CUDA errors or crashes: grep -i "cuda\|segfault\|undefined behavior" /var/log/vllm/*.log
Verify the fix by confirming version is >= 0.23.1: pip show vllm | grep Version

FAQ

What is CVE-2026-54235?

CVE-2026-54235 is a vulnerability in vLLM's temperature parameter validation that fails to reject NaN and positive Infinity values, allowing them to propagate to GPU sampling kernels and cause crashes or undefined behavior.

Is CVE-2026-54235 being actively exploited?

No, there is no evidence of active exploitation in the wild, and no public exploit code is available. However, the vulnerability can be triggered by malformed API requests, so defense-in-depth measures are recommended.

What versions of Python are affected by CVE-2026-54235?

vLLM versions prior to 0.23.1 are affected. The vulnerability exists in all releases up to and including 0.23.0, regardless of the underlying Python version.

How do I check if my server is vulnerable to CVE-2026-54235?

Run 'python3 -c "import vllm; print(vllm.__version__)"' and verify the version is 0.23.1 or later. If version is 0.23.0 or earlier, your deployment is vulnerable.

Does Defensia detect CVE-2026-54235?

Yes — Defensia's CVE advisory scanner compares installed package versions against the NVD database. If vLLM is installed on a monitored server, CVE-2026-54235 will appear in your dashboard with remediation steps.

Related Python CVEs

CVE-2026-25632CVSS 10EPyT-Flow is a Python package designed for the easy generation of hydraulic and water quality scenario data of water distribution networks. Prior to 0.16.1, EPyT-Flow’s REST API parses attacker-controlled JSON request bodies using a custom deserializer (my_load_from_json) that supports a type field. When type is present, the deserializer dynamically imports an attacker-specified module/class and instantiates it with attacker-supplied arguments. This allows invoking dangerous classes such as subprocess.Popen, which can lead to OS command execution during JSON parsing. This also affects the loading of JSON files. This vulnerability is fixed in 0.16.1.

CVE-2026-34938CVSS 10PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.

CVE-2026-33054CVSS 10Mesop is a Python-based UI framework that allows users to build web applications. Versions 1.2.2 and below contain a Path Traversal vulnerability that allows any user supplying an untrusted state_token through the UI stream payload to arbitrarily target files on the disk under the standard file-based runtime backend. This can result in application denial of service (via crash loops when reading non-msgpack target files as configurations), or arbitrary file manipulation. This vulnerability heavily exposes systems hosted utilizing FileStateSessionBackend. Unauthorized malicious actors could interact with arbitrary payloads overwriting or explicitly removing underlying service resources natively outside the application bounds. This issue has been fixed in version 1.2.3.

CVE-2026-28505CVSS 10Tautulli is a Python based monitoring and tracking tool for Plex Media Server. Prior to version 2.17.0, the str_eval() function in notification_handler.py implements a sandboxed eval() for notification text templates. The sandbox attempts to restrict callable names by inspecting code.co_names of the compiled code object. However, co_names only contains names from the outer code object. When a lambda expression is used, it creates a nested code object whose attribute accesses are stored in code.co_consts, NOT in code.co_names. The sandbox never inspects nested code objects. This issue has been patched in version 2.17.0.

CVE-2026-26030CVSS 9.9Semantic Kernel, Microsoft's semantic kernel Python SDK, has a remote code execution vulnerability in versions prior to 1.39.4, specifically within the `InMemoryVectorStore` filter functionality. The problem has been fixed in version `python-1.39.4`. Users should upgrade this version or higher. As a workaround, avoid using `InMemoryVectorStore` for production scenarios.

References

Track CVEs across your fleet automatically

Defensia scans your Linux servers and tells you exactly which ones are running vulnerable versions — including CVE-2026-54235. Free for 1 server.

Get started free