vllm-project · vLLM · published 2026-04-06
CVE-2026-34755vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
Routine No exploitation evidence; EPSS 0.5%.
CVE-2026-34755 is not known to be exploited in the wild. EPSS estimates a 0.5% chance of exploitation in the next 30 days, higher than 42% of all CVEs. This vLLM vulnerability: CVSS 6.5 (v3.1). Fixed upstream in vLLM 0.19.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.19.0.
Patch events
AI toolingvLLM
vLLM security release: 0.19.0
Upgrade to
0.19.0Why: Vendor security release for server software (most severe: CVE-2026-34755).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.5% (42th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 6.5 (v3.1)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
>= 0.7.0, < 0.19.0(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.