{"id":"CVE-2026-115912","published":"2026-10-26T17:17:18.910","lastModified":"2026-10-26T20:17:51.793","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.","cvssScore":7.5,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H","cwes":["CWE-502"],"vendors":[],"products":[],"references":[{"url":"https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0","tags":[]},{"url":"https://github.com/vllm-project/vllm/pull/59357","tags":[]},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.32.0","tags":[]},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w","tags":[]}],"exploitRefs":[{"url":"https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0","tags":[]},{"url":"https://github.com/vllm-project/vllm/pull/59357","tags":[]},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.32.0","tags":[]},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w","tags":[]}],"hasPoc":true,"ai":null}