CVE-2026-76841Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders
- 8.7HighCVSS base score
- 1.0%Exploitation in 30 daysEPSS · top 36% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- NonePublic exploitsnone known yet
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.
Timeline
ID reserved
By VulnCheck
- 5 days later
· 5 days later
Published
- 38 days later
· 38 days later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| VulnCheckCNA (assigner) | 4.0 | High8.7 | 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 |
| VulnCheckCNA (assigner) | 3.1 | High8.8 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| NVDNVD · Deferred | 4.0 | High8.7 | 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 |
- EPSS (exploitation in 30 days)
- 1.0% · top 36% of all CVEs (14 Nov 2026)
- CISA SSVC
- Exploitation: none · Automatable: no · Technical impact: total
The list uses the assigner's score when there is one, then CISA's, then NVD's: High 8.7.
Affected products
References
References5
- https://github.com/xorbitsai/inference (opens in a new tab)product
- https://github.com/xorbitsai/inference/issues/5023 (opens in a new tab)issue-tracking
- https://github.com/xorbitsai/inference/pull/5027 (opens in a new tab)issue-trackingpatch
- https://github.com/xorbitsai/inference/blob/v2.11.0/xinference/model/rerank/core.py (opens in a new tab)technical-description
- VulnCheck Advisory: Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders (opens in a new tab)third-party-advisory
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2026-64847 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisories (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2026-76841)Record last updated .