CVE-2026-73560

Published: Ago 17, 2026 Last Modified: Ago 17, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 6,5
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Scope: unchanged
Confidentiality: high
Integrity: none
Availability: none

Description

AI Translation Available

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.

918

Server-Side Request Forgery (SSRF)

Incomplete
Common Consequences
Security Scopes Affected:
Confidentiality Integrity Access Control
Potential Impacts:
Read Application Data Execute Unauthorized Code Or Commands Bypass Protection Mechanism
Applicable Platforms
Technologies: Web Based, AI/ML, Web Server
View CWE Details
https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42…
https://github.com/vllm-project/vllm/pull/43117
https://github.com/vllm-project/vllm/releases/tag/v0.26.0
https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7