UTC
Medium

vLLM: Speech-to-text upload size limit is enforced after full UploadFile read

CVE-2026-55646 · GHSA-v82g-2437-67m2 · published 2026-07-17

Severity
Medium
CVSS score
6.5
Chance of exploitation (EPSS)
0.52%
Fixed in
0.24.0
  • Exploitation Public proof of concept
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

Attack requirements: the deployment exposes /v1/audio/transcriptions or /v1/audio/translations; a speech-to-text capable model/task is configured; and the caller can submit requests to the endpoint, including any API key the deployment requires. An API caller who meets those requirements can send an oversized audio file. vLLM reads the full uploaded file into memory before applying the configured compressed audio file-size limit. This can create memory pressure or, depending on process/container limits and concurrency, terminate the process before the request is rejected. Suggested severity: Moderate, ), CWE-770/CWE-400. The impact is availability-only.

What to do

Upgrade vllm to 0.24.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Enforce the compressed audio upload limit before the unbounded read: Check reliable upload size metadata before reading when available. Read at most max_bytes + 1 bytes in chunks as a defense-in-depth guard against missing or unreliable metadata. Share the helper between transcription and translation routes. Add regression tests that prove an over-limit UploadFile is rejected without calling an unbounded read(). The important property is that over-limit compressed uploads are rejected before vLLM allocates the full uploaded file as bytes.

Affected
PackageRegistryAffectedFixed in
vllmPyPI>= 0.22.0, < 0.24.00.24.0

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].