Servers and applications
GHSA-p6g9-7v3x-m8mv
Remote media is fetched and fully materialized before the documented media size / item limits are enforced — remote pre-inference memory and bandwidth exhaustion (4 sites)
- Severity
- Medium 6.5
- Published
- 12 Sept 2026
- Last changed
- 12 Sept 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.29.0
- Attack
- Over the network · Needs a user account · No user action needed
- Attacker can
- Take it down
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H- Sources
- Project advisories (GitHub)
Description
vLLM documents several media controls as protection against out-of-memory denial of service: a compressed audio filesize cap (VLLM_MAX_AUDIO_CLIP_FILESIZE_MB, default 25 MB), per-modality item limits (--limit-mm-per-prompt), and a general guidance to restrict media decode sizes. Each of these is premised on oversized or over-count media being rejected before the process commits memory. Across four ingress paths, the media-acquisition layer instead performs the expensive work first — it fully reads the HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part — and only then applies the documented limit (or, on some paths, never applies it).
A single request can therefore make the API-server or batch-runner process allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected.
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · github:vllm-project/vllm |
|
About vLLM
open-source software for large language model inference
- Docker Hub pulls
- 44,195,225Docker Hub, 15 Nov 2026
- GitHub stars
- 96,943GitHub, 15 Nov 2026
- Forks
- 24,836GitHub, 15 Nov 2026
- Latest release
- v0.33.0rc3GitHub, 15 Nov 2026
- Released
- 2 Nov 2026GitHub
- License
- Apache Software License 2.0Wikidata
- First published on GitHub
- 9 Feb 2023GitHub
Website Source code Docker image
Vulnerabilities in vLLM
- In our list
- 169
- Published in the last 12 months
- 150
- Critical, last 12 months
- 6
- High, last 12 months
- 63
- Known exploited
- 0
- CVE-2026-130686vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image RequestsHigh 8.7 18 Nov 2026
- CVE-2026-130684vLLM before 0.33.0 Path Traversal via speculators_config verifier.name_or_pathMedium 5.3 18 Nov 2026
- CVE-2026-130685vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token IDHigh 8.7 18 Nov 2026
- GHSA-xgh8-qwjh-q853/v1/systemone bypasses the --trust-request-chat-template gateMedium 6.5 18 Nov 2026
- CVE-2026-129356vllm-project vllm Common Prefix single_type_kv_cache_manager.py race conditionLow 2.3 15 Nov 2026
- CVE-2026-126394vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_framesMedium 6.9 13 Nov 2026
References
- GitHub Advisory Database https://github.com/advisories/GHSA-p6g9-7v3x-m8mv
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv