CVE-2026-73560
MEDIUM
MEDIUM
Priority: 0.03
BB Relevance:
63/100
Published: 2026-08-17
Modified: 2026-10-23
First seen: 2026-10-29
Status: active
Attack Surface
Network
Low Complexity
No Interaction
Conf. Impact
CVSS Vector Breakdown
AV:
Network
AC:
Low
PR:
Low
UI:
None
S:
Unchanged
C:
High
I:
None
A:
None
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.
Weakness Classification (1)
References & Advisories (4)
Release Notes
Patch
Mitigation
Vendor Advisory
Issue Tracking
Patch