CVE-2026-73560

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

Published Aug 17, 2026 CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

The vulnerability resides in the MiMoV2OmniMultiModalProcessor of vLLM, where attacker‑controlled image and audio strings are passed to a custom fetch routine that uses requests.get and Image.open instead of the intended MediaConnector. This bypasses the library’s allowed_media_domains and allowed_local_media_path checks, enabling the server to make outbound requests to arbitrary URLs and to read any files the vLLM process can access. The impact is a direct server‑side request forgery and potential disclosure of local files that may contain sensitive data, a weakness classified under CWE‑918.

Affected Systems

The issue affects vllm‑project’s vLLM engine in all releases prior to version 0.26.0. No specific minor versions are listed; any build before the fix is vulnerable.

Risk and Exploitability

The CVSS score is 6.5, signifying moderate severity. The EPSS score is not available, and the vulnerability is not listed in the CISA KEV catalog. An attacker who can submit image or audio inputs to the processor can trigger the flaw, potentially accessing arbitrary remote resources or local files. Because the vulnerability relies on normal API usage and does not require elevated privileges, the likelihood of exploitation is considered moderate and should be treated as a significant concern for exposed services.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade vLLM to version 0.26.0 or later, which contains the fix for the processor.
  • If upgrading is not immediately possible, disable or block the custom _fetch_image routine and route all media inputs through MediaConnector to enforce domain and path restrictions.
  • Restrict the vLLM process file‑system permissions or run it in a sandboxed environment to prevent reading sensitive local files.

Generated by OpenCVE AI on August 17, 2026 at 22:05 UTC.

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Github GHSA Github GHSA GHSA-4hhp-h66f-j5j7 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
History
Type Values Removed Values Added
First Time appeared Vllm
Vllm vllm
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm
Type Values Removed Values Added
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.
Title vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
Weaknesses CWE-918
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N'}

Weaknesses
  • CWE-918

    Server-Side Request Forgery (SSRF)

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Aug 18, 2026, 4:00 PM
Reserved
Aug 12, 2026, 8:53 PM
Status
Analyzed
Published
Aug 17, 2026, 9:16 PM
Modified
Oct 23, 2026, 4:10 PM
Severity
Moderate
Public date
Aug 17, 2026, 8:17 PM