{"apiVersion":"1.0","identifier":"CVE-2026-73560","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.","publishedAt":"2026-08-17T21:16:48","lastModifiedAt":"2026-08-18T16:18:17","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-73560","cvssScore":6.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","epssProbability":0.00319,"riskScore":0.67,"affectedProduct":"vLLM","affectedVersions":"<0.26.0","vulnerabilityType":"Library","operatingSystems":[],"links":{"self":"https://www.redsauce.net/api/cves/CVE-2026-73560","webPages":{"es":"https://www.redsauce.net/es/cves/CVE-2026-73560","en":"https://www.redsauce.net/en/cves/CVE-2026-73560","fr":"https://www.redsauce.net/fr/cves/CVE-2026-73560","pt":"https://www.redsauce.net/pt/cves/CVE-2026-73560","de":"https://www.redsauce.net/de/cves/CVE-2026-73560","sk":"https://www.redsauce.net/sk/cves/CVE-2026-73560","el":"https://www.redsauce.net/el/cves/CVE-2026-73560"},"source":"https://nvd.nist.gov/vuln/detail/CVE-2026-73560"}}