Vulnerabilities · 2025 · Vllm
CVE-2025-46722
Vllm vulnerability
vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.
Affected products
Vllm. The exact versions are in the references.
What to do now
- Check your exposureFind out whether Vllm runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6 · Vendor Advisory
- github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848 · Patch
- github.com/vllm-project/vllm/pull/17378 · Patch
- nvd.nist.gov/vuln/detail/CVE-2025-46722
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-43.yaml
- github.com/advisories/GHSA-c65p-x677-fgj6
- nvd.nist.gov/vuln/detail/CVE-2025-46722
- cve.org/CVERecord?id=CVE-2025-46722
More vulnerabilities in Vllm products
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.