Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-76841— Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders

Quick assessment

Affected
xorbitsai inference
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Xinference 在未条件限制的情况下，通过启用 Hugging Face 的远程代码执行功能来加载模型，且在 2.12.0 版本之前，没有任何设置可以禁用该功能。六个加载点将 作为字面量或无条件默认值传递： 中的 中的 中的 中的 以及 中的两个站点，其中 和 将值默认设置为 由于具有模型启动权限的调用者可以注册未知类型的模型并提供任意模型路径，服务器会进入 方法，然后调用 ，这会导入并执行由模型目录中 的 声明的 Python 代码，从而以工作进程的特权运行攻击者提供的代码。在 2.12.0 版本中，所有相

CVSS 8.8 · High EPSS 0.71% · P51

Possible ATT&CK Techniques 1 AI

T1190 · Exploit Public-Facing Application

Affected Version Matrix 1

VendorProduct Version RangeStatus
xorbitsai inference < 2.12.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-76841

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
xorbitsai inference 0 ~ 2.12.0 -

II. Public POCs for CVE-2026-76841

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 8592 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-76841

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-76841 (2)

Vendor Advisories for CVE-2026-76841 (1)

Exploits & Public PoCs for CVE-2026-76841 (1)

Other References for CVE-2026-76841 (1)

IV. Related Vulnerabilities

Same product: inference
Same vendor: xorbitsai
Same weakness: CWE-94

V. Comments for CVE-2026-76841

No comments yet

Leave a comment