All vulnerabilities

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
Weakness
Decompression bomb (CWE-409)CWE-807CWE-1284
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.

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.28.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.28.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
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

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