CVE-2026-55646 vllm vulnerability
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.
Quick answer
vllm should be reviewed and updated if it matches the affected versions. The recommended fix is to apply the vendor-supported patched version or the mitigation steps below, then retest the public website with Fixnx.
Who is affected
Affected versions
- Review vendor advisory for affected versions.
Fixed versions
- Apply the latest vendor-supported patched version.
How to fix it
vLLM is affected by CVE-2026-55646, a cross-site scripting risk. vLLM is an inference and serving engine for large language models. The recommended remediation is to update to vLLM 0.24.0 or later. Until the update is complete, enforce upload size limits before reading audio files into memory and restrict transcription/translation endpoints until patched, review logs, and reduce exposure of the affected service, firmware path, or build workflow.
- Inventory every deployment, package, firmware image, appliance, device family, container, build runner, or service that uses vLLM.
- Confirm the installed version or firmware build and compare it with versions from 0.22.0 through 0.23.0 and the source advisory for CVE-2026-55646.
- Apply the vendor-supported fix: update to vLLM 0.24.0 or later.
- If the update cannot be applied immediately, enforce upload size limits before reading audio files into memory and restrict transcription/translation endpoints until patched; disable unnecessary public access, endpoints, uploads, build inputs, hardware features, or high-risk integrations until patched.
- Review application, device, kernel, firmware, build, package manager, container, authentication, and audit logs for activity related to CVE-2026-55646.
- Rotate sessions, API tokens, service credentials, signing keys, integration keys, and administrator passwords if logs or affected data indicate compromise, code execution, credential exposure, or unauthorized access.
- Clear caches, restart affected services, rebuild affected containers or firmware images when appropriate, and remove temporary files, generated artifacts, stored payloads, or unsafe configuration created during exploitation attempts.
Scan now. Google sign-in is only needed to unlock fix guidance.
Verify the fix
- Confirm vLLM now reports vLLM 0.24.0 or later or a later vendor-supported fixed release/build for the deployed branch or device family.
- Verify the affected workflow no longer allows the behavior described in CVE-2026-55646, using a safe regression test, vendor validation method, or firmware/package inventory check.
- Review logs after remediation for continued exploit attempts, denial-of-service symptoms, suspicious redirects, unauthorized requests, file access, memory corruption symptoms, or configuration changes.
- Rerun a Fixnx scan and any product-specific scanner, package audit, firmware inventory, device health check, or manual regression test relevant to the affected service.
- Document affected assets, fixed versions, mitigation decisions, validation evidence, and any cleanup, rebuild, or credential rotation performed.
Related categories
Trusted references
FAQ
What is affected by CVE-2026-55646?
vllm should be checked against the vendor advisory and trusted references linked on this page.
What should I fix first?
Start with internet-facing sites, admin panels, login flows, plugins, themes, modules, packages, and systems that process user-controlled input or sensitive data.
How do I confirm the fix worked?
Apply the patched version or mitigation, clear caches where relevant, retest the affected workflow, and run a new Fixnx scan to verify public website exposure signals.
How are Fixnx security risk categories chosen?
Fixnx keeps one canonical risk page and assigns only broad, relevant categories such as ecosystem, technology area, or vulnerability class.