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.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0 Patch
- https://github.com/vllm-project/vllm/pull/59357 Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w Patch, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 9
- Cpes+1 CPE criteria (now 1)NVD modified 2026-10-28 15:38
- StatusPublished → AnalyzedNVD modified 2026-10-28 15:38
- CVSS7.5 (v3.1, CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H) → 8.8 (v3.1, CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H)NVD modified 2026-10-28 15:38
- StatusAwaiting Analysis → PublishedNVD modified 2026-10-26 19:35
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-26 20:17
- StatusAwaiting Analysis → PublishedNVD modified 2026-10-26 16:54
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-26 18:34
- StatusReceived → PublishedNVD modified 2026-10-26 16:54
- First seenCVSS 7.5NVD modified 2026-10-26 17:17
Affected (CPE criteria) 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References 4
- https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0 Patch
- https://github.com/vllm-project/vllm/pull/59357 Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w Patch, Vendor Advisory