{"id":"CVE-2026-76841","revision":"ccf575f0d9e24ce6b19ae42dada8e63f","records":[{"revision":"ccf575f0d9e24ce6b19ae42dada8e63f","observedAt":"2026-10-23T15:48:27.903+00:00","statement":{"source":"cve-program","id":"CVE-2026-76841","aliases":[],"title":"Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders","description":"Xinference loads models with Hugging Face remote code execution unconditionally enabled, and before version 2.12.0 exposes no setting to disable it. Six loader call sites pass trust_remote_code=True as a literal or as an unconditional default: RerankModel._get_tokenizer in xinference/model/rerank/core.py, SentenceTransformerRerankModel.load in xinference/model/rerank/sentence_transformers/core.py, SentenceTransformerEmbeddingModel.load in xinference/model/embedding/sentence_transformers/core.py, FlagEmbeddingModel.load in xinference/model/embedding/flag/core.py, and two sites in xinference/model/llm/transformers/core.py where PytorchModel._sanitize_model_config and PytorchModel._get_components default the value to True. Because a caller with model launch access can register a model whose type is unknown and supply an arbitrary model path, the server reaches _auto_detect_type and then AutoTokenizer.from_pretrained, which imports and executes Python declared by the model directory's own tokenizer_config.json auto_map, running attacker-supplied code with the privileges of the worker process. Version 2.12.0 gates every site behind allow_trust_remote_code and the XINFERENCE_TRUST_REMOTE_CODE setting, permitting remote code only for bundled built-in models.","state":0,"publishedAt":"2026-08-24T13:11:59.094+00:00","modifiedAt":"2026-10-01T15:21:12.439+00:00","affected":[{"ecosystem":"https://pypi.org/project/xinference/","name":"xinference","ranges":[],"versions":[],"rawVersionEvidence":"{\n                    \"vendor\": \"xorbitsai\",\n                    \"product\": \"inference\",\n                    \"collectionURL\": \"https://pypi.org/project/xinference/\",\n                    \"packageName\": \"xinference\",\n                    \"packageURL\": \"pkg:pypi/xinference\",\n                    \"defaultStatus\": \"unaffected\",\n                    \"versions\": [\n                        {\n                            \"version\": \"0\",\n                            \"lessThan\": \"2.12.0\",\n                            \"status\": \"affected\",\n                            \"versionType\": \"semver\"\n                        }\n                    ]\n                }"}],"metrics":[{"system":"CVSS 4.0","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","score":8.7,"severity":"HIGH"},{"system":"CVSS 3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H","score":8.8,"severity":"HIGH"}],"references":["https://github.com/xorbitsai/inference","https://github.com/xorbitsai/inference/issues/5023","https://github.com/xorbitsai/inference/pull/5027","https://github.com/xorbitsai/inference/blob/v2.11.0/xinference/model/rerank/core.py","https://www.vulncheck.com/advisories/xinference-through-remote-code-execution-via-hardcoded-trust-remote-code-in-model-loaders"],"sourceUrl":"https://www.cve.org/CVERecord?id=CVE-2026-76841","license":"CVE Program Terms of Use","key":"cve-program:CVE-2026-76841","identifiers":["CVE-2026-76841"]},"retained":false,"historicalAffected":[]}],"coverage":[]}