THREATOPS
THREAT OPS › Threat News › [NVD] CVE-2026-73560 (MEDIUM 6.5) — 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 instea

[NVD] CVE-2026-73560 (MEDIUM 6.5) — 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 instea

lownvdPublished 2026-08-17

CVE-2026-73560 CVSS: 6.5 MEDIUM Published: 2026-08-17T21:16:48.960

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

Indicators of compromise

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