CVEFinder.io

CVE-2026-34755

🔶 medium
🔍 Scan for this CVE
Summary

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 co

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.

CVSS Score
6.5
Medium
EPSS Score
0.1
Exploit Probability
Published Date
2026-04-06
First Seen: 2026-04-07
📊 Relative Risk Intelligence

This CVE is Lower Risk - more severe than 47.8% of all 326,604 vulnerabilities in our database.

#170,379
Below average severity
Severity Percentile
🎯 CISA SSVC Assessment Updated: Apr 6, 2026
🔍 Exploitation Status
None
No known exploits
⚙️ Automatable
NO
Requires human interaction
💥 Technical Impact
Partial
Limited system impact
SSVC data provided by CISA
Last Modified 2026-04-20
Source NVD 🔗
CVSS Vector 3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CWE IDs (Weakness Types)
CWE-770

📦 Affected Products 1

Vendor Product Status Affected Versions
vllm vllm Affected
> 0.7.0 < 0.19.0

🔗 References 1

https://github.com/vllm-project/vllm/security/adviso...
Patch Vendor Advisory

🔗 Related CVEs 6

CVE ID Severity CVSS EPSS Summary Published
CVE-2026-44222 🔶 medium 6.5 0.0 vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Toke... 2026-05-12
CVE-2026-44223 🔶 medium 6.5 0.0 vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_sta... 2026-05-12
CVE-2026-7141 🔶 medium 5.6 0.1 A vulnerability was found in vllm up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v... 2026-04-27
CVE-2026-34753 🔶 medium 5.4 0.0 vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side re... 2026-04-06
CVE-2026-34756 🔶 medium 6.5 0.0 vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Servi... 2026-04-06
CVE-2026-34760 🔶 medium 5.9 0.1 vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, L... 2026-04-02
These CVEs affect the same products