CVE-2026-73560

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

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.

Scores

Weaknesses (CWE)

• CWE-918

Advisories

• GHSA-4hhp-h66f-j5j7 — vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
• PYSEC-2026-3934 — vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

European references

• ENISA EUVD · EUVD-2026-60377
• GCVE · GCVE-0-2026-73560

Affected configurations (NVD CPE)

• cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* < 0.26.0

Affected products

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7
• https://github.com/vllm-project/vllm/pull/43117
• https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5
• https://github.com/vllm-project/vllm/releases/tag/v0.26.0

Sources