Vulnerability · Published Aug 17, 2026 · Assigned by GitHub_M

CVE-2026-73560vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Medium 6.5

In plain English

A medium-severity server-side request forgery in vllm from vllm-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 35% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium
Exploit odds (30 days)0.4%top 64.8% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official 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 packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIvllm0.26.0GHSA-4hhp-h66f-j5j7
PyPIvllm0.26.0PYSEC-2026-3934

Affected products (as reported)

VendorProductVersions
vllm-project vllm < 0.26.0

Weakness: CWE-918 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

References