PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-73560 vllm-project CVE debrief

CVE-2026-73560 is a vulnerability in the vLLM inference and serving engine for large language models. 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. This allows server-side requests and reads of arbitrary files accessible to the vLLM process. The issue is fixed in version 0.26.0.

Vendor
vllm-project
Product
vllm
CVSS
MEDIUM 6.5
CISA KEV
Not listed in stored evidence
Original CVE published
2026-08-17
Original CVE updated
2026-09-28
Advisory published
2026-08-17
Advisory updated
2026-09-28

Who should care

Defenders responsible for deploying and managing vLLM inference and serving engines should assess exposure and apply the patch to prevent potential unauthorized file access. This includes operators managing vLLM deployments, platform administrators, vulnerability management teams, and security teams responsible for monitoring and incident response.

Why it matters

CVE-2026-73560 is a vulnerability in the vLLM inference and serving engine that allows server-side requests and file reads. Defenders should prioritize verifying exposure and applying the patch to prevent potential unauthorized file access.

  • Potential unauthorized file access.
  • Possible server-side request forgery.
  • Required verification of exposure and patch application.
  • Potential data breaches or system compromise.

Technical summary

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. This allows server-side requests and reads of arbitrary files accessible to the vLLM process, potentially leading to unauthorized file access or data breaches. The issue is fixed in version 0.26.0, and defenders should prioritize verifying exposure and applying the patch.

Defensive priority

Defenders should prioritize verifying exposure and applying the patch to prevent potential unauthorized file access.

Recommended defensive actions

  • Verify if the vLLM process has access to sensitive files or directories.
  • Apply the patch by upgrading to version 0.26.0 or later.
  • Monitor for potential unauthorized file access attempts.
  • Review and update allowed_media_domains and allowed_local_media_path protections.
  • Review compensating controls for exposed systems while remediation is scheduled and verified.
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review.
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented.

Evidence notes

The CVE record and NVD entry provide details on the vulnerability, affected versions, and fixed version. Evidence is limited to public sources and may not reflect the full scope of potentially affected systems or the specific impacts on all environments. Defenders should verify exposure by reviewing system configurations, checking for vulnerable versions of vLLM, and assessing if sensitive files or directories are accessible to the vLLM process.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-73560 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-73560

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-73560 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-73560

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.