Description
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0.
Affected products
vllm: vllm
References5
- github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f… MitigationVendor Advisory
- github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f… MitigationVendor Advisory
- github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f286… Patch
- github.com/vllm-project/vllm/pull/43117 Issue TrackingPatch
- github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
Metrics
- CVSS 3.1
-
6.5
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N - EPSS — exploit probability
- 0% percentile: 35 · as of 11 November 2026
- CWE
- CWE-918
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.