NIST deprecates RSA-2048 from 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
MEDIUM severity

vLLM vulnerable to Denial of Service by abusing xgrammar cacheGHSA-hf3c-wxg2-49q9

MEDIUMFix: vllm-project/vllm#16283

GHSA-hf3c-wxg2-49q9 is a medium-severity (CVSS 6.5) vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Apr 15, 2025 · OSV.dev, FIRST.org (EPSS)

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Impact

This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3

The xgrammar library is the default backend used by vLLM to support structured output (a.k.a. guided decoding). Xgrammar provides a required, built-in cache for its compiled grammars stored in RAM. xgrammar is available by default through the OpenAI compatible API server with both the V0 and V1 engines.

A malicious user can send a stream of very short decoding requests with unique schemas, resulting in an addition to the cache for each request. This can result in a Denial of Service by consuming all of the system's RAM.

Note that even if vLLM was configured to use a different backend by default, it is still possible to choose xgrammar on a per-request basis using the guided_decoding_backend key of the extra_body field of the request with the V0 engine. This per-request choice is not available when using the V1 engine.

Patches

Workarounds

There is no way to workaround this issue in existing versions of vLLM other than preventing untrusted access to the OpenAI compatible API server.

References

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm≥ 0.6.5&&< 0.8.40.8.4pip install --upgrade 'vllm==0.8.4'

Detection & mitigation playbook

Open-source dependency

  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update vllm to 0.8.4 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-hf3c-wxg2-49q9 is resolved across your whole dependency graph.

  3. Workarounds

    Cap what an attacker can consume: apply request size, rate and timeout limits in front of the affected component, and run it with memory and CPU limits so exhaustion degrades one worker rather than the whole service.

Frequently Asked Questions

### Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The [xgrammar](https://xgrammar.mlc.ai/docs/) library is the default backend used by vLLM to support structured output (a.k.a. guided decoding). Xgrammar provides a required, built-in cache for its compiled grammars stored in RAM. xgrammar is available by default through the OpenAI compatible API server with both the V0 and V1 engines. A malicious user can send a
O3 Security · Impact-Aware SCA

Is GHSA-hf3c-wxg2-49q9 in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works
vLLM vulnerable to Denial of Service by abusing…