AI Threat Alert

CVE-2026-76841

HIGH
Published August 24, 2026

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...

Full CISO analysis pending enrichment.

How severe is it?

CVSS 3.1
8.8 / 10
EPSS
N/A
Exploitation Status
No known exploitation
Sophistication
N/A

What is the attack surface?

AV AC PR UI S C I A
AV Network
AC Low
PR Low
UI None
S Unchanged
C High
I High
A High

What should I do?

No patch available

Monitor for updates. Consider compensating controls or temporary mitigations.

Which compliance frameworks are affected?

Compliance analysis pending. Sign in for full compliance mapping when available.

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.

Is CVE-2026-76841 actively exploited?

No confirmed active exploitation of CVE-2026-76841 has been reported, but organizations should still patch proactively.

How to fix CVE-2026-76841?

No patch is currently available. Monitor vendor advisories for updates.

What is the CVSS score for CVE-2026-76841?

CVE-2026-76841 has a CVSS v3.1 base score of 8.8 (HIGH).

What are the technical details?

Original Advisory

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.

Weaknesses (CWE)

CWE-94 Improper Control of Generation of Code ('Code Injection') Primary

CWE-94 — Improper Control of Generation of Code ('Code Injection'): The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.

  • [Architecture and Design] Refactor your program so that you do not have to dynamically generate code.
  • [Architecture and Design] Run your code in a "jail" or similar sandbox environment that enforces strict boundaries between the process and the operating system. This may effectively restrict which code can be executed by your product. Examples include the Unix chroot jail and AppArmor. In general, managed code may provide some protection. This may not be a feasible solution, and it only limits the impact to the operating system; the rest of your application may still be subject to compromise. Be careful to avoid CWE-243 and other weaknesses related to jails.

Source: MITRE CWE corpus.

CVSS Vector

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

References

Timeline

Published
August 24, 2026
Last Modified
August 24, 2026
First Seen
August 24, 2026
Back to Threat Feed