High · CVSS 8.7CVE-2026-109225

SGLang through 0.5.21 Memory Exhaustion DoS via /v1/audio/transcriptions UploadCVE-2026-109225

Answer in brief

CVE-2026-109225 records a High severity (CVSS 8.7) vulnerability in SGLang through 0.5.21 Memory Exhaustion DoS via /v1/audio/transcriptions Upload. The current sources do not mark it as known exploited. The current feed maps sgl-project/sglang (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Oct 12, 2026Updated Oct 12, 2026Source checked Oct 12, 2026First seen by HOL Oct 12, 2026Material review Oct 12, 2026

Upstream Advisory

Key facts

Risk: High · CVSS 8.7
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Not reported

Why this deserves its current priority

CVSS is 8.7. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps sgl-project/sglang (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
sgl-project/sglanggeneric	>=0 <=0.5.21	Not reported

Recommended response

Check inventory. Check lockfiles and deployed manifests for sgl-project/sglang.
Review the reported fix. Monitor this advisory for an available fix and review any installs of the affected package.

Evidence timeline and material changes

Published upstream
Oct 12, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Oct 12, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Oct 12, 2026

Sources and claim methodology

Upstream source description

SGLang through 0.5.21 contains an unbounded memory allocation vulnerability that allows unauthenticated remote attackers to exhaust memory by uploading oversized files to /v1/audio/transcriptions. Attackers can send concurrent large multipart uploads, which are fully read into memory before validation, to crash the HTTP/tokenizer worker and deny service.

Quoted source text, attributed separately from HOL analysis.