{"cve":"CVE-2025-46722","nvd":{"published":"2025-05-29T17:15:21.523","modified":"2026-06-17T09:26:52.583","status":"Analyzed","description":"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.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L","score":7.3},"cwes":["CWE-1023","CWE-1288"],"references":["https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848","https://github.com/vllm-project/vllm/pull/17378","https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:01:57.636215869+00:00"},"epss":{"cve":"CVE-2025-46722","score":0.00338,"percentile":0.27238,"date":"2026-10-31"},"kev":null,"osv":[{"id":"GHSA-c65p-x677-fgj6","url":"https://osv.dev/vulnerability/GHSA-c65p-x677-fgj6","summary":"vLLM has a Weakness in MultiModalHasher Image Hashing Implementation","modified":"2026-08-07T08:12:03.917531780Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":[">=0.7.0 <0.9.0"],"fixed":["0.9.0"]}]},{"id":"PYSEC-2025-43","url":"https://osv.dev/vulnerability/PYSEC-2025-43","summary":"","modified":"2025-05-29T19:42:13.122057Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.9.0"],"fixed":["0.9.0"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}