Summary
vLLM : DoS via unvalidated mmprocessorkwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)
API clients can supply arbitrary mm_processor_kwargs per request. vLLM
forwards these values through the multimodal rendering and processing pipeline
to Hugging Face and custom image/video processor constructors and calls.
Resource-sensitive values such as image size, patch size, patch count, crop
count, or frame count can therefore be controlled by a remote client.
For processors that upscale inputs, a single request can force an allocation
large enough to terminate the API server or worker with an out-of-memory
condition.
Affected Components
The per-request field was introduced in commit041e29471671a3d43afedb6a749421d56ef4d3e7 and first shipped in v0.7.3.
The generic forwarding path remains present in current main.
The Isaac path is a concrete high-amplification example:
ChatCompletionRequest.mm_processor_kwargsOnlineRendererrequest extrasMMProcessorInputs.hf_processor_mm_kwargsBaseMultiModalProcessor.info.get_hf_processor(**hf_processor_mm_kwargs)IsaacProcessingInfo.get_image_processor(**kwargs)IsaacImageProcessor(**kwargs)process_vision_for_patches()
Equivalent constructor forwarding exists in InternVL-derived processors,
H2OVL, Step3VL, NemotronVL, and other multimodal processors. The issue is at
the shared remote-input boundary and is not limited to a fixed model list.
Impact
- Availability: one request can exhaust CPU or GPU memory and terminate a
shared service process. - Scope: all users of the affected service instance lose availability.
- Authentication: vLLM's API key is optional, so deployments without an
external authentication layer are remotely reachable without privileges.
Crafted input forces the application to consume excessive CPU, memory, or other resources, degrading or denying service. Typical impact: denial of service.
CVE-2026-114055 has a CVSS score of 7.5 (High). The vector is network-reachable, no privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.31.0); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Reject non-empty per-request mm_processor_kwargs at every API-server request
schema by default. Operators serving only trusted clients can explicitly opt
in to the existing override behavior. Server-level --mm-processor-kwargs and
offline LLM overrides remain available.
This shared boundary covers current and future multimodal processors instead
of maintaining a model-specific list or a denylist that can miss custom
processor arguments.
A patch for this was merged here: https://github.com/vllm-project/vllm/pull/58830
Frequently Asked Questions
- What is CVE-2026-114055? CVE-2026-114055 is a high-severity uncontrolled resource consumption vulnerability in vllm (pip), affecting versions >= 0.7.3, < 0.31.0. It is fixed in 0.31.0. Crafted input forces the application to consume excessive CPU, memory, or other resources, degrading or denying service.
- How severe is CVE-2026-114055? CVE-2026-114055 has a CVSS score of 7.5 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of vllm are affected by CVE-2026-114055? vllm (pip) versions >= 0.7.3, < 0.31.0 is affected.
- Is there a fix for CVE-2026-114055? Yes. CVE-2026-114055 is fixed in 0.31.0. Upgrade to this version or later.
- Is CVE-2026-114055 exploitable, and should I be worried? Whether CVE-2026-114055 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-114055 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-114055? Upgrade
vllmto 0.31.0 or later.