Servers and applications
CVE-2026-90555
Speech-to-text audio decode duration limit bypass via forged header sample rate
- Severity
- High 7.1
- Published
- 28 Aug 2026
- Last changed
- 16 Sept 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.28.0
- Exploit chance
- 0.5% in the next 30 daysHigher than 44% of CVEs. EPSS by FIRST, 19 Nov 2026
- Attack
- Over the network · Needs a user account · No user action needed
- Attacker can
- Take it down
- CVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/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-99f2-hwrc-gvq8
- Sources
- NVD, Project advisories (GitHub)
Description
The fix for GHSA-6pr9-rp53-2pmc / CVE-2026-54233 (PR #44970, commit 1b1359c33) added a max_duration_s guard to audio decoding that, on the primary soundfile code path, computes duration as f.frames / f.samplerate - both values read directly from the attacker-supplied container header before any decode. An authenticated API client can POST a small (≤200 KB) 8-channel FLAC with header sample_rate=655350 to /v1/audio/transcriptions; the guard sees a duration of a few seconds and passes, after which f.read(dtype="float32") allocates hundreds of MB to ~12 GiB of float32 PCM in the API-server process, causing an OOM-kill and denial of service for all tenants. The PyAV fallback branch of the same fix is robust (it counts decoded samples), but is not reached for files that soundfile parses successfully.
The vulnerability lets an authenticated remote API client crash the shared API-server process, crossing the API client → API server (heap) trust boundary.
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-2026-90555
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-90555
- GitHub Advisory Database https://github.com/advisories/GHSA-99f2-hwrc-gvq8
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-99f2-hwrc-gvq8