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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-918"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73560.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "0.26.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.26.0",
"range": [
{
"fixed": "568afb3a13806beb53bb2e6bd518269357b237c0"
}
],
"source": "REFERENCES_TAG"
}
]
}