high7.5
CVE-2026-115912
vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
Impact
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.
Affected packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | vllm | < 0.32.0 | 0.32.0 |
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Vllm | Vllm | before 0.32.0 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/advisories/GHSA-6757-hggm-hp2w
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w
- https://nvd.nist.gov/vuln/detail/CVE-2026-115912
- https://github.com/vllm-project/vllm/pull/59357
- https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0