Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
HIGH severity

vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)GHSA-gx7p-2j49-hfq4

HIGHFix: vllm-project/vllm#58830

GHSA-gx7p-2j49-hfq4 is a high-severity (CVSS 7.5) Uncontrolled Resource Consumption vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

Also known asCVE-2026-114055
Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Oct 22, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for GHSA-gx7p-2j49-hfq4.

EPSS Exploitation Probability

via FIRST.org ↗
0.3%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs27th percentile — riskier than 27% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

GHSA-gx7p-2j49-hfq4 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.

Where this sits among everything scored

Of 394,803 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.

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

Summary

API clients can supply arbitrary mm_processor_kwargs per request. vLLM forwards these values through the multimodal rendering and processing pipeline to Hugging Face and custom image/video processor constructors and calls. Resource-sensitive values such as image size, patch size, patch count, crop count, or frame count can therefore be controlled by a remote client.

For processors that upscale inputs, a single request can force an allocation large enough to terminate the API server or worker with an out-of-memory condition.

Affected Components

The per-request field was introduced in commit 041e29471671a3d43afedb6a749421d56ef4d3e7 and first shipped in v0.7.3. The generic forwarding path remains present in current main.

The Isaac path is a concrete high-amplification example:

  • ChatCompletionRequest.mm_processor_kwargs
  • OnlineRenderer request extras
  • MMProcessorInputs.hf_processor_mm_kwargs
  • BaseMultiModalProcessor.info.get_hf_processor(**hf_processor_mm_kwargs)
  • IsaacProcessingInfo.get_image_processor(**kwargs)
  • IsaacImageProcessor(**kwargs)
  • process_vision_for_patches()

Equivalent constructor forwarding exists in InternVL-derived processors, H2OVL, Step3VL, NemotronVL, and other multimodal processors. The issue is at the shared remote-input boundary and is not limited to a fixed model list.

Impact

  • Availability: one request can exhaust CPU or GPU memory and terminate a shared service process.
  • Scope: all users of the affected service instance lose availability.
  • Authentication: vLLM's API key is optional, so deployments without an external authentication layer are remotely reachable without privileges.

Remediation

Reject non-empty per-request mm_processor_kwargs at every API-server request schema by default. Operators serving only trusted clients can explicitly opt in to the existing override behavior. Server-level --mm-processor-kwargs and offline LLM overrides remain available.

This shared boundary covers current and future multimodal processors instead of maintaining a model-specific list or a denylist that can miss custom processor arguments.

A patch for this was merged here: https://github.com/vllm-project/vllm/pull/58830

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm≥ 0.7.3&&< 0.31.00.31.0pip install --upgrade 'vllm==0.31.0'

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 0.31.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-gx7p-2j49-hfq4 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

## Summary API clients can supply arbitrary `mm_processor_kwargs` per request. vLLM forwards these values through the multimodal rendering and processing pipeline to Hugging Face and custom image/video processor constructors and calls. Resource-sensitive values such as image size, patch size, patch count, crop count, or frame count can therefore be controlled by a remote client. For processors that upscale inputs, a single request can force an allocation large enough to terminate the API server or worker with an out-of-memory condition. ## Affected Components The per-request field was intr
O3 Security · Impact-Aware SCA

Is GHSA-gx7p-2j49-hfq4 in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works
vLLM : DoS via unvalidated mm_processor_kwargs in…