CVE-2026-76841: Code Injection (CVSS 8.8)

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.

Is your site exposed to CVE-2026-76841?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

8.8

HIGH

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

EPSS — Exploit Prediction

0.0071

Probability of exploitation

0.52%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-94 CWE-94

References

Other References

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

Frequently Asked Questions

What is 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. It has a CVSS v3.1 base score of 8.8 (HIGH).

How severe is CVE-2026-76841? +

CVE-2026-76841 has a CVSS v3.1 score of 8.8 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0071, placing it in the 1th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-76841? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-22136

Tabby (formerly Terminus) is a highly configurable terminal emulator. Prior to 1.0.217 , Tabby enables several high-risk Electron Fuses, including …

CVE-2025-24482

A Local Code Injection Vulnerability exists in the product and version listed above. The vulnerability is due to incorrect default …

CVE-2026-72717

Orval generates type-safe JavaScript clients in TypeScript from OpenAPI v3 and Swagger v2 specifications. Prior to 8.21.0, a ${...} expression …

CVE-2026-77077

n8n versions before 1.123.69, 2.33.4, and 2.34.1 contain a JavaScript task runner VM sandbox escape. The runner's prototype-freezing routine covers …

CVE-2026-59859

Kiota is an OpenAPI based HTTP Client code generator. Prior to 1.32.4, Kiota's PHP generator embedded OpenAPI description, default fields, …

CVE-2026-59865

Kiota is an OpenAPI based HTTP Client code generator. Prior to 1.32.5, `kiota info` read x-ms-kiota-info.languagesInformation.<language>.dependencyInstallCommand plus dependency name and …

CVE-2026-76841