vLLM
vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
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.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS8.8high · scored by NVD · CWE-502
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
vllm-project vllm
- < 0.32.0
Fixed in 0.32.0
Mitigation
Upgrade vllm to 0.32.0 or later.
References
- Vendor advisory github.com/vllm-project/vllm/security/advisori…
- Patch github.com/vllm-project/vllm/pull/59357
- Patch github.com/vllm-project/vllm/commit/3d5625cc3c…
1 more
- Release notes github.com/vllm-project/vllm/releases/tag/v0.3…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.