CVE-2026-76841
What it is
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.
At a glance
- Exploitability
- Can be exploited over the network with a low-privilege account. High risk of data exposure, data tampering, service disruption.
- Exploit odds
- 1.0% chance of exploitation in the next 30 days (EPSS).
- Fix
- A patch, advisory or fixed version is referenced. Upgrade or apply it.
Timeline
- PublishedDisclosed publicly on CVE.org and NVD
- Last updatedMost recent change to the record
Why it ranks here
- Exploited in the wild: no, CISA does not list it.
- Exploit odds: 1.0% in the next 30 days (EPSS).
- Severity: 8.7 HIGH (CVSS).
- Fix: a patch or advisory is linked.
Details
- Published
- Last modified
- Exploit probability
- 1.0% · EPSS, next 30 days
- Weakness
- CWE-94 · Code injection
- Record status
- Deferred
Attack profile CVSS 4.0 · 8.7
- Attack vector
- Network
- Complexity
- Low
- Attack requirements
- None
- Privileges needed
- Low
- User interaction
- None
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Raw 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Is it in your code?
Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.
Read https://cve-list.com/agent/cve/CVE-2026-76841.md and follow it. Check whether this project is affected by CVE-2026-76841. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.
Fix and advisories
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