How severe is CVE-2026-34755?

CVE-2026-34755 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is none, integrity none, and availability high.

Is CVE-2026-34755 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (30th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2026-34755?

CVE-2026-34755 affects Vllm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-34755?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.

Does CVE-2026-34755 have an EU (EUVD) identifier?

Yes. CVE-2026-34755 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-19350.

When was CVE-2026-34755 published?

CVE-2026-34755 was published on 2026-04-06 and last updated on 2026-07-07.

CVE-2026-34755

CVE-2026-34755 is a medium-severity vulnerability in Vllm with a CVSS 3.x base score of 6.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-770.

Key facts

Severity: Medium (CVSS 3.x base score 6.5)
EPSS exploit prediction: 0% (30th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-19350
Weakness: CWE-770
Affected product: Vllm
Published: 2026-04-06
Last modified: 2026-07-07

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.

Frequently asked questions

What is CVE-2026-34755?: vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
How severe is CVE-2026-34755?: CVE-2026-34755 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is none, integrity none, and availability high.
Is CVE-2026-34755 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (30th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-34755?: CVE-2026-34755 affects Vllm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-34755?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
Does CVE-2026-34755 have an EU (EUVD) identifier?: Yes. CVE-2026-34755 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-19350.
When was CVE-2026-34755 published?: CVE-2026-34755 was published on 2026-04-06 and last updated on 2026-07-07.

References

Affected products (1)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

More vulnerabilities in Vllm

CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
CVE-2026-48746 — Critical (CVSS 9.1): vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in…
CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…

All CVEs affecting Vllm →

Other CWE-770 (Allocation of Resources Without Limits or Throttling) vulnerabilities

CVE-2026-31283 — Critical (CVSS 9.8): In Totara LMS v19.1.5 and before, the forgot password API does not implement rate limiting for the target email…
CVE-2020-37067 — Critical (CVSS 9.8): Filetto 1.0 FTP server contains a denial of service vulnerability in the FEAT command processing that allows attackers…
CVE-2021-47875 — Critical (CVSS 9.8): GeoGebra CAS Calculator 6.0.631.0 contains a denial of service vulnerability that allows attackers to crash the…
CVE-2025-11832 — Critical (CVSS 9.8): Allocation of Resources Without Limits or Throttling vulnerability in Azure Access Technology BLU-IC2, Azure Access…
CVE-2024-44241 — Critical (CVSS 9.8): The issue was addressed with improved bounds checks. This issue is fixed in iOS 18.1 and iPadOS 18.1, macOS Sequoia…
CVE-2022-3439 — Critical (CVSS 9.8): Allocation of Resources Without Limits or Throttling in GitHub repository ikus060/rdiffweb prior to 2.5.0.

Browse all CWE-770 (Allocation of Resources Without Limits or Throttling) vulnerabilities →