CVE-2026-73560
vLLM is an inference and serving engine for large language models. …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5
- github.com/vllm-project/vllm/pull/43117
- github.com/vllm-project/vllm/releases/tag/v0.26.0
- github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7
- nvd.nist.gov/vuln/detail/CVE-2026-73560
- github.com/advisories/GHSA-4hhp-h66f-j5j7
- nvd.nist.gov/vuln/detail/CVE-2026-73560
- cve.org/CVERecord?id=CVE-2026-73560
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.