CVE-2026-73560

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.

Traduire en français

Produits concernés

• vllm-project vllm
• Vllm vllm

Scores CVSS

Faiblesses (CWE)

• CWE-918

Références

• https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5 Patch
• https://github.com/vllm-project/vllm/pull/43117 Issue TrackingPatch
• https://github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
• https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7 MitigationVendor Advisory
• https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7 MitigationVendor Advisory

Ailleurs

• NVD
• CVE.org
• CIRCL Vulnerability-Lookup
• CERT-FR
• GitHub Advisories