CVE-2026-100653

HIGH 8.3

Published 2026-09-26 · Last modified 2026-10-01

vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/funaudiochat.py and the Qwen2VLConfig.from_pretrained call used by Tarsier2ProcessingInfo in vllm/model_executor/models/qwen2_vl.py. As a result, deployments pinned to a reviewed revision still resolve these behavior-affecting processor, tokenizer, and config artifacts from the repository's default revision, so a later change to the upstream default branch can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration without any change to the operator's configured pin. This is a supply-chain integrity and reproducibility failure for pinned deployments; it is residual to the earlier fix tracked as GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 and does not constitute remote code execution or a trust_remote_code=False bypass. The issue is fixed in version 0.28.0.

ELEVATED IMPACT

Severe if exploited (CVSS 8.3), but no known exploitation and low modeled probability. Patch on a normal cadence.

Exploitation likelihood

0.3%chance of exploitation in 30 days · 27th percentile

○ In CISA KEV ○ Catalogued PoC

Impact if exploited

8.3CVSS 4.0 · HIGH

ConfidentialityLow
IntegrityHigh
AvailabilityNone

What an attacker needs

✓Access: Reachable over the network — no local access needed
✓Privileges: No account or privileges required
✓User interaction: No user interaction needed
⚠Complexity: Needs a race window or specific setup
⚠Requirements: Specific conditions must be present

✓ lowers the bar for an attacker · ⚠ raises it

Proof of concept

No public PoC is currently catalogued.

Search for new PoCs

Search GitHub now — results may be empty or unverified.

Tracked sources are checked daily for recent CVEs, including PoCs published after the original disclosure. A later release appears after a tracked source lists it and a refresh succeeds.

Data snapshot: 2026-10-26T13:52:32.101Z

Affected

Vendors Vllm Project Vllm

Products Vllm

Weakness (CWE)

CWE-348: Use of Less Trusted Source

CVSS vector

CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

References and research data (JSON)

Packages and version ranges

Each advisory describes its own package and affected ranges. A boundary applies to that range; it is not a universal upgrade recommendation.

vllm PyPI

pkg:pypi/vllm
ECOSYSTEM range
- Introduced version (included): 0.22.1
- Fixed boundary (excluded): 0.28.0
8 explicitly listed affected versions
0.22.1, 0.23.0, 0.24.0, 0.25.0, 0.25.1, 0.26.0, 0.27.0, 0.27.1
Additional upstream package constraints
```
{
  "ecosystem": {},
  "database": {
    "source": "https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4324.yaml"
  }
}
```
PyPA · PYSEC-2026-4324 · Updated 2026-10-23T19:00:39.873437407Z

Vendor product assessments

rhaii/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-cpu-rhel9@sha256:81c5994dc20321f8bd3969099eade78ef127cbd79f2d0ccea101c773e4c7fa4d?repository_url=registry.redhat.io/rhaii/vllm-cpu-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaii/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-cuda-rhel9@sha256:0d22e2301ce26ef68effda5d3a4a20381ad0ea34d1240e159e245bd44c2e125b?repository_url=registry.redhat.io/rhaii/vllm-cuda-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaii/vllm-gaudi-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-gaudi-rhel9@sha256:ce1e4fd82dd37d299ce8c64a237971d00faf602f06868c986e81aefa04c283ef?repository_url=registry.redhat.io/rhaii/vllm-gaudi-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaii/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-neuron-rhel9@sha256:1079c9afecdbc33f4790792f0d712dbf7523790a92dcfbe8fb5cf4c2d282fc5b?repository_url=registry.redhat.io/rhaii/vllm-neuron-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaii/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-rocm-rhel9@sha256:1a30359d6ca5d0891e403b9b0a23c0ae1ad6e30a2429b9b42e246b874fe8859a?repository_url=registry.redhat.io/rhaii/vllm-rocm-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaii/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-spyre-rhel9@sha256:11ad6e13c41728944d933c7abe01d1d10ecb3f8e8b4f0da50ec53b7df6f036a8?repository_url=registry.redhat.io/rhaii/vllm-spyre-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaii/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-tpu-rhel9@sha256:0c2ac747d67dc0e80162ff05867dd702e474b2217659f19f28b8e3a0c03a942a?repository_url=registry.redhat.io/rhaii/vllm-tpu-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaiis/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-cpu-rhel9@sha256:fb7791bbfea99e9f81529fe8cc1e7c834ca470585c27590e3d0a6834167cd436?repository_url=registry.redhat.io/rhaiis/vllm-cpu-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaiis/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-cuda-rhel9@sha256:73bbc4560132c4aaa9bbd608ce9560eeae7b30bcc8f014da460afa5622139372?repository_url=registry.redhat.io/rhaiis/vllm-cuda-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-neuron-rhel9@sha256:8ba72cec5d79b1a751eb09774c81fd6181b43ec69a2e5116982661b34366874d?repository_url=registry.redhat.io/rhaiis/vllm-neuron-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaiis/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-rocm-rhel9@sha256:37b64a8df90756aae0ee96d2f07765adbce5ed5beb2414ac3845806ad2219cfc?repository_url=registry.redhat.io/rhaiis/vllm-rocm-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaiis/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-spyre-rhel9@sha256:3dd7eff1c62cd4609b4c76590b77bb801cd064e40642ed32b5aa900a6bc643ea?repository_url=registry.redhat.io/rhaiis/vllm-spyre-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhaiis/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server · known affected

Vendor assessment for this product only.

pkg:oci/vllm-tpu-rhel9@sha256:b1c12112a1e8a298645e10d34d44c9961a6121aa8d87fc5d65ad83e1ffa3c586?repository_url=registry.redhat.io/rhaiis/vllm-tpu-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-aws-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-aws-cuda-rhel9@sha256:a754d4d1126e98f203249414b3831182bb15ee6b3643452f167849defc642e4b?repository_url=registry.redhat.io/rhelai3/bootc-aws-cuda-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-azure-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-azure-cuda-rhel9@sha256:df5b6edd1bdb055219a7385b6d5923f3262c3a408f92da734e3027af55fd593f?repository_url=registry.redhat.io/rhelai3/bootc-azure-cuda-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-azure-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-azure-rocm-rhel9@sha256:8ea1233b1fb6b82d0aa69e9e4c47d2df242001280c11a61584066c27c5bec3a5?repository_url=registry.redhat.io/rhelai3/bootc-azure-rocm-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-cuda-rhel9@sha256:b45f3bc25a7d3c9f3bfdc1de3be6db59f6c3109f62326d74fae14e832a797981?repository_url=registry.redhat.io/rhelai3/bootc-cuda-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-gaudi-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-gaudi-rhel9@sha256:e1057b59ca1be9501332abf97230855e85c7df858356be0da9dce230ea7e98e1?repository_url=registry.redhat.io/rhelai3/bootc-gaudi-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-gcp-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-gcp-cuda-rhel9@sha256:bac5d435d156c3ddcb581d3ff05fdce9f72bd617c5b8435cede16bb17b7bf12e?repository_url=registry.redhat.io/rhelai3/bootc-gcp-cuda-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3 · known affected

Vendor assessment for this product only.

pkg:oci/bootc-rocm-rhel9@sha256:38ce057f97034bbb8eaea574d41cc7eebaeaa9265a4cdd966476dd3fac129c3c?repository_url=registry.redhat.io/rhelai3/bootc-rocm-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-kserve-agent-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-kserve-agent-rhel9@sha256:eddf436baf8906d08f1cd28fecdc73f70f9bbf11a73e327d9c97495ee921c523?repository_url=registry.redhat.io/rhoai/odh-kserve-agent-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-kserve-controller-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-kserve-controller-rhel9@sha256:8b4d4c6a45b2ff1b25fda45dc022066ed5d055267ce08ab0b31e58191970632e?repository_url=registry.redhat.io/rhoai/odh-kserve-controller-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-kserve-router-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-kserve-router-rhel9@sha256:1fb5c0b39c43904a5843a9e01cddac40cfe5580d9bb7abdf6083c9f53d1655b3?repository_url=registry.redhat.io/rhoai/odh-kserve-router-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-kserve-storage-initializer-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-kserve-storage-initializer-rhel9@sha256:7c88948bcfa0fc3439b1eae31c426639346044505aff440238bfb194fd15ce99?repository_url=registry.redhat.io/rhoai/odh-kserve-storage-initializer-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-llm-d-kv-cache-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-llm-d-kv-cache-rhel9@sha256:cb5eedeefd2578cd9bd8637250bbe299c84539f57b4ead75d630ed9f833a6ef2?repository_url=registry.redhat.io/rhoai/odh-llm-d-kv-cache-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-th-torch-cuda-py312-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-th-torch-cuda-py312-rhel9@sha256:efd7b3607b699092c68359d20ef0d0043114191a097637667c0d2cf78fbea702?repository_url=registry.redhat.io/rhoai/odh-th-torch-cuda-py312-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
rhoai/odh-vllm-gaudi-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · known affected

Vendor assessment for this product only.

pkg:oci/odh-vllm-gaudi-rhel9@sha256:87eec3862eb6ddef445f89dcf6fd89add7ef202ea7c563b1ee7347537fb3e250?repository_url=registry.redhat.io/rhoai/odh-vllm-gaudi-rhel9
- workaround: Pre-download the vetted model repository to local storage and configure offline execution. 1. Download the specific, verified commit revision of the model to a local directory: huggingface-cli download <MODEL_NAME> --revision <REVISION_HASH> --local-dir /path/to/local/model 2. Configure the environment to disable remote Hub requests and launch vLLM using the local path: export HF_HUB_OFFLINE=1 vllm serve /path/to/local/model For containerized environments (such as Red Hat OpenShift AI or Red Hat Enterprise Linux AI), set the environment variable HF_HUB_OFFLINE=1 in the container deployment specification and mount the pre-downloaded model volume into the container filesystem. Caveats: Deployments require sufficient local or persistent volume storage to host model weights and configurations. Warning: Modifying the deployment configuration or environment variables requires restarting the serving container or service, resulting in temporary inference downtime.
- none available: Fix deferred
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00

Known Affected Software Configurations

Vendor	Product	Version range
Vllm	Vllm	≥ 0.22.1 and < 0.28.0

All CVSS metrics

HIGH 8.3 v4.0 · CNA Primary
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N
MEDIUM 6.5 v3.1 · CNA Primary
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N
HIGH 8.3 v4.0 · NVD Secondary
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
MEDIUM 6.5 v3.1 · NVD Secondary
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N

References

Exploit-tagged references (not proof of a PoC)

https://github.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628q vendor-advisoryexploitExploitMitigationVendor AdvisoryEVIDENCEvendor-referenceCVE record · VulnCheck · Updated 2026-10-01T11:06:45.139Z
CVE record · CISA-ADP · Updated 2026-09-30T17:46:36.993Z
NVD · CVE-2026-100653 · Updated 2026-10-20T18:35:50.567
PyPA · PYSEC-2026-4324
PyPA · PYSEC-2026-4324 · Updated 2026-10-23T19:00:39.873437407Z
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00

Patches & mitigations

https://github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6 patchPatchFIXvendor-referenceCVE record · VulnCheck · Updated 2026-10-01T11:06:45.139Z
NVD · CVE-2026-100653 · Updated 2026-10-20T18:35:50.567
PyPA · PYSEC-2026-4324
PyPA · PYSEC-2026-4324 · Updated 2026-10-23T19:00:39.873437407Z
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00

Advisories

https://www.vulncheck.com/advisories/vllm-0.22.1-before-0.28.0-incomplete-artifact-pin-propagation third-party-advisoryThird Party AdvisoryADVISORYvendor-referenceCVE record · VulnCheck · Updated 2026-10-01T11:06:45.139Z
NVD · CVE-2026-100653 · Updated 2026-10-20T18:35:50.567
PyPA · PYSEC-2026-4324
PyPA · PYSEC-2026-4324 · Updated 2026-10-23T19:00:39.873437407Z
Red Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
https://osv.dev/vulnerability/PYSEC-2026-4324 ADVISORYPyPA · PYSEC-2026-4324
PyPA · PYSEC-2026-4324 · Updated 2026-10-23T19:00:39.873437407Z
https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-100653.json vendor-advisoryRed Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-87747 ADVISORYEUVD · EUVD-2026-87747

Technical & other

https://access.redhat.com/security/cve/CVE-2026-100653 vendor-referenceRed Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
https://bugzilla.redhat.com/show_bug.cgi?id=2541818 vendor-referenceRed Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
https://www.cve.org/CVERecord?id=CVE-2026-100653 vendor-referenceRed Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00
https://nvd.nist.gov/vuln/detail/CVE-2026-100653 vendor-referenceRed Hat · CVE-2026-100653 · Updated 2026-10-01T17:34:09+00:00

Sources: NVD · CVE.org · EPSS