Is CVE-2026-93436 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-93436 being exploited in the wild.

How severe is CVE-2026-93436?

High severity, with a CVSS score of 7.5, published 17 September 2026.

Which products and versions are affected?

vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.30.0; Vllm through 0.29.0.

Is there a fix for CVE-2026-93436?

Yes. vllm (PyPI): upgrade to 0.30.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

How is CVE-2026-93436 attacked?

It is attacked over the network, in a software library.

Am I affected by CVE-2026-93436?

Check whether you run vllm (PyPI) or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2026-93436: vLLM memory exhaustion in decode-side metadata cleanup

CVE-2026-93436 · Severity: high · CVSS 7.5 · Published 2026-09-17

vLLM is a high-throughput inference engine for large language models (LLMs) commonly used to serve AI applications. In disaggregated deployments (where prefill and decode processing are split across separate workers), vLLM fails to clean up decode metadata when requests are rejected, allowing an attacker to exhaust decode-worker memory by submitting specially crafted requests, eventually forcing worker restarts and service disruption.

Technologies: vllm (PyPI), Vllm. Vendors: PyPI, Vllm.

Quick answers

Is CVE-2026-93436 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-93436 being exploited in the wild.
How severe is CVE-2026-93436?: High severity, with a CVSS score of 7.5, published 17 September 2026.
Which products and versions are affected?: vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.30.0; Vllm through 0.29.0.
Is there a fix for CVE-2026-93436?: Yes. vllm (PyPI): upgrade to 0.30.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-93436 attacked?: It is attacked over the network, in a software library.
Am I affected by CVE-2026-93436?: Check whether you run vllm (PyPI) or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

vllm (PyPI): upgrade to 0.30.0 or later
```
pip install "vllm>=0.30.0"
```

Technical details

This is a resource exhaustion vulnerability in vLLM's distributed inference system, specifically in the decode-side metadata cleanup logic for disaggregated prefill/decode deployments. The vulnerability occurs when inference requests with max_tokens=0 are submitted; these requests are rejected but the associated metadata is not properly cleaned up from the decode worker's memory. A remote attacker can repeatedly submit such requests over the network to unbounded exhaustion of heap memory, eventually triggering out-of-memory conditions and forcing decode worker restarts. The vulnerability affects vLLM through version 0.29.0, and patches should be available in later releases.

Affected products

vLLM vLLM through 0.29.0

Identifiers

CVE-2026-93436
PYSEC-2026-3996

Timeline

2026-09-17: disclosed
other: CVE-2026-93436 assigned

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.