# CVE-2026-34755: vLLM denial of service via unbounded video frame processing

Source: https://junglewise.ai/threats/cve-2026-34755-vllm-denial-of-service-via-unbounded-video-frame-processing  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-04-06. Updated: 2026-06-30  
License: CC BY 4.0 with a link back

CVE-2026-34755 · Severity: medium · CVSS 6.5 · Published 2026-04-06

vLLM is a high-performance engine used to serve Large Language Models (LLMs) to users and applications. A vulnerability in how it processes video data allows an attacker to send a specially crafted request that consumes all available server memory. This can lead to a complete service crash, resulting in a denial of service for all users of the AI platform.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Red Hat AI Inference Server](https://junglewise.ai/threats/technologies/ai-inference-server), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Red Hat](https://junglewise.ai/threats/vendors/red-hat), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2026-34755 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-34755 being exploited in the wild.

**How severe is CVE-2026-34755?** Medium severity, with a CVSS score of 6.5, published 6 April 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0.7.0,fixed=0.19.0; Red Hat AI Inference Server 3.

**Is there a fix for CVE-2026-34755?** Yes. vllm (PyPI): upgrade to 0.19.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-34755 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-34755?** Check whether you run vllm (PyPI), Red Hat AI Inference Server 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 0.19.0 or later

  ```sh
  pip install "vllm>=0.19.0"
  ```


## Technical details

The vulnerability exists in the VideoMediaIO.load_base64() method within vllm/multimodal/media/video.py. While the load_bytes() path correctly enforces a 'num_frames' limit (default 32), the load_base64() path for 'video/jpeg' MIME types uses an unbounded split operation on comma-separated data URLs. An attacker with network access and low privileges can submit a single API request containing thousands of base64-encoded JPEG frames. Each frame is decoded into a full numpy array in memory, leading to rapid memory exhaustion (OOM) and a process crash. This issue is tracked as CWE-770 and is resolved in version 0.19.0.

## Affected products

- vllm-project vLLM >= 0.7.0, < 0.19.0
- Red Hat Red Hat AI Inference Server 3
- Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 3
- Red Hat Red Hat OpenShift AI (RHOAI)

## Identifiers

- CVE-2026-34755
- GHSA-pq5c-rjhq-qp7p
- PYSEC-2026-144

## Timeline

- 2026-04-03: advisory: GitHub Security Advisory published
- 2026-04-06: disclosed: CVE-2026-34755 published to NVD
- 2026-04-06: patched: Fix released in version 0.19.0

## References

- [https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p](https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p)
- [https://access.redhat.com/security/cve/CVE-2026-34755](https://access.redhat.com/security/cve/CVE-2026-34755)
- [https://bugzilla.redhat.com/show_bug.cgi?id=2455403](https://bugzilla.redhat.com/show_bug.cgi?id=2455403)
- [https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)