CVE-2026-115912

vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

Published Oct 26, 2026 CVSS 3.1 · 7.5 High EPSS < 1% KEV · Not listed
Description
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.

Analysis

AI-generated

Technical impact

The flaw in vLLM allows an authenticated caller to forge shared‑memory handle and monotonic_id values in the public multimodal features.kwargs_data field. When scale‑out deployments enable shared‑memory multimodal caching, the worker trusts these values and forwards the attacker‑chosen byte stream to Python's pickle.loads, even when insecure serialization is disabled. This results in arbitrary Python code execution, which can compromise the host or any other users sharing the same worker process.

Affected Systems

All installations of the vLLM inference and serving engine prior to version 0.32.0 are affected. The vulnerability applies to the vllm-project:vllm product when deployed in scale‑out mode with shared‑memory multimodal caching activated. Proper upgrades beyond 0.32.0 mitigate the risk.

Risk and Exploitability

The CVSS score of 7.5 indicates a high‑severity risk. Although the EPSS score is not available and the issue is not listed in CISA KEV, the attack requires an authenticated victim in a scale‑out configuration. Once authenticated, the attacker can craft malicious data that is deserialized by worker processes, enabling full code execution on the host. The vulnerability is exploitable in practice in environments where shared‑memory multimodal caching is enabled and the insecure serialization option is disabled, making it a realistic threat vector for administrators who manage vLLM services.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade the vLLM engine to version 0.32.0 or later, where the shared‑memory forgery handling has been fixed.
  • If an upgrade is not immediately possible, disable shared‑memory multimodal caching in the deployment configuration to prevent workers from trusting forged handle data.
  • Restrict access to the public multimodal features interface so that only trusted, privileged users can submit data, reducing the window for forgery attempts.

Generated by OpenCVE AI on October 26, 2026 at 18:26 UTC.

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Github GHSA Github GHSA GHSA-6757-hggm-hp2w vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Type Values Removed Values Added
First Time appeared Vllm
Vllm vllm
Vllm-project
Vllm-project vllm
Vendors & Products Vllm
Vllm vllm
Vllm-project
Vllm-project vllm
Type Values Removed Values Added
Description vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.
Title vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
Weaknesses CWE-502
References
Metrics cvssV3_1

{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H'}

Weaknesses
  • CWE-502

    Deserialization of Untrusted Data

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Oct 26, 2026, 7:35 PM
Reserved
Oct 23, 2026, 8:21 PM
Status
Analyzed
Published
Oct 26, 2026, 5:17 PM
Modified
Oct 28, 2026, 3:38 PM
Severity
Important
Public date
Oct 26, 2026, 4:54 PM