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

Severity: medium (CVSS 6.5 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.8% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2026-09-26 · updated 2026-10-06
Weakness: CWE-400

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.

Affected products

vllm-project vllm: through 0.29.0

References

Get alerted when CVE-2026-100650 or the next vulnerability affects your stack