CVE-2026-76841

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.

• CWE-94

• https://github.com/xorbitsai/inference
• https://github.com/xorbitsai/inference/blob/v2.11.0/xinference/model/rerank/core.py
• https://github.com/xorbitsai/inference/issues/5023
• https://github.com/xorbitsai/inference/pull/5027
• https://www.vulncheck.com/advisories/xinference-through-remote-code-execution-via-hardcoded-trust-remote-code-in-model-loaders

Published

Aug 24, 2026

Last Modified

Aug 26, 2026

Status

Received

• How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
• Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
• PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
• AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.

• CVE-2026-76836AzuraCast exposes the Liquidsoap custom configuration fields…8.8
• CVE-2026-76837Baserow interpolates a user's display name into the rich-tex…6.4
• CVE-2026-76838Hi.Events validates a webhook destination only when it is re…8.5
• CVE-2026-76839Grav before 2.0.16 allows sandboxed Twig templates to access…6.5
• CVE-2026-7684A security vulnerability has been detected in Edimax BR-6428…8.8
• CVE-2026-76840RustDesk's Windows clipboard redirection copies a peer-suppl…9.6
• CVE-2026-76842The Mercado Pago Node.js SDK interpolates caller-supplied id…8.2
• CVE-2026-76843The official Flair wheels for 0.15.0 and 0.15.1 still contai…7.8
• CVE-2026-76844webpack-dev-middleware resolves a request to a local file in…7.4
• CVE-2026-76845adm-zip 0.5.9 through 0.6.0 follows symbolic links at the ex…6.5
• CVE-2026-76846Grav before 2.0.16 contains an incomplete default denylist i…7.5
• CVE-2026-76847act starts an HTTP Artifacts V4 backend whenever a workflow …8.8