Servers and applications
CVE-2026-100648
Uncontrolled resource consumption: multimodal chat audio decoding ignores `VLLM_MAX_AUDIO_CLIP_FILESIZE_MB`
- Severity
- Medium 6.9
- Published
- 12 Sept 2026
- Last changed
- 6 Oct 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.29.0
- Exploit chance
- 0.4% in the next 30 daysHigher than 29% of CVEs. EPSS by FIRST, 19 Nov 2026
- Attack
- Over the network · No login needed · No user action needed
- Attacker can
- Slow it down
- CVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X- Also known as
- GHSA-jcq2-4gch-5qhf
- Sources
- NVD, Project advisories (GitHub)
Description
MediaConnector.fetch_audio passes multimodal chat audio bytes directly to AudioMediaIO.load_bytes without checking VLLM_MAX_AUDIO_CLIP_FILESIZE_MB (vllm/multimodal/media/connector.py:449-462, vllm/multimodal/media/audio.py:231-251).
The speech-to-text upload path enforces the same setting before the full file is decoded (vllm/entrypoints/speech_to_text/base/utils.py:14-64). The multimodal chat path therefore bypasses the documented per-file limit.
An unauthenticated client of a public OpenAI-compatible chat endpoint can make the server materialize and decode an audio file larger than the configured limit, consuming memory and CPU that the limit is intended to bound.
The chat message parser passes each audio URL to the shared media connector (vllm/entrypoints/chat_utils.py:1054-1058,1252-1255). MediaConnector.fetch_audio constructs AudioMediaIO and calls load_from_url:
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · cpe:a:vllm:vllm |
|
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
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-100648
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-100648
- GitHub Advisory Database https://github.com/advisories/GHSA-jcq2-4gch-5qhf
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-jcq2-4gch-5qhf