7.1

CVE-2026-100650: vLLM before 0.29.0 Resource Exhaustion via Unbounded Media Materialization

Analyzed
AliasesPYSEC-2026-4184GHSA-p6g9-7v3x-m8mv
Published 26-09-2026Last modified 01-10-2026

Vulnerability summary

CVE-2026-100650 is a high (CVSS 7.1) Uncontrolled Resource Consumption vulnerability in vllm-project vllm. EPSS estimates a 0.65% chance of exploitation in the next 30 days, higher than 50.6% of scored vulnerabilities. 1 public exploit is recorded.

Overall risk
39/100
0100
Medium · default modelHow is this calculated?
CVSS score
7.1/10
010
High · v4.0 (CVE.org)
EPSS score
0.65%
0%100%
Low · Change unavailable
KEVNot listedNot listed by any tracked catalog.
RansomwareNot flaggedNo ransomware use recorded.
Public exploits1github

Timeline

  1. 26-09-2026
    PublishedVulnerability first disclosed.
  2. 01-10-2026
    Last modifiedVulnerability information updated.

Description

vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.

CVSS metrics

5 scores · 3 sources · 2 versions

EPSS trend

Probability

0.65%

Chance of exploitation in the next 30 days

Percentile

51%

Versus all other CVEs

30-day change

Change unavailable

Change unavailable

27-09-202622-10-2026

Known exploited

Compare KEV catalogs
CISA KEV

Not in the CISA KEV catalog.

ENISA CNW

Not in the ENISA CNW catalog.

CIRCL

Not in the CIRCL catalog.

Public exploits

1 found
  • githubUnverified

    Vllm

    Maturity: poc

Weaknesses

CWE · root cause

Affected systems

PyPI1 product
  • vllm< 0.30.0
Vllm1 product
Vllm-project1 product

3 vendors · 3 products

References

3 links