CVE-2026-76841 — Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders
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.
Who exploits it and how urgent it is
A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.
How the score was calculated
- EPSS 1% (30-day exploitation probability)+9
- Technical severity (high)+6
The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).
Triage
Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.
CISA SSVC assessment CISA
Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.
Remediation
Fixes and mitigations documented by the sources — linked to the original advisory.
No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.
First 24 hours
Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.
- Identify exposed assets running the affected vendor/product/version combinations (Xorbitsai Inference).
- No fix documented in the sources: reduce exposure and monitor the vendor advisory.
- Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.
Affected scope
Vendor, product and versions as the sources word them.
Attack characteristics
The CVSS vector, decoded. It describes the attack, not your exposure to it.
Every base score collected
Sources score independently and may disagree; each row says who scored it and under which version.
| Score | Version | Severity | Expl. | Impact | Scored by |
|---|---|---|---|---|---|
| 8.7 | CVSS 4.0 | High | — | — | disclosure@vulncheck.com via NIST National Vulnerability Database |
| 8.7 | CVSS 4.0 | High | — | — | VulnCheck via CVE Program (cve.org) e CISA ADP |
| 8.8 | CVSS 3.1 | High | 2.8 | 5.9 | disclosure@vulncheck.com via NIST National Vulnerability Database |
| 8.8 | CVSS 3.1 | High | — | — | VulnCheck via CVE Program (cve.org) e CISA ADP |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H (score shown at the top: disclosure@vulncheck.com) Weakness MITRE
Weakness class according to MITRE’s CWE catalog.
EPSS over time FIRST
Oct 13, 2026 → Oct 15, 2026 · 3 reading(s) · max 1.03%
Detection
Read off the CVSS vector and the weakness class. Starting points, not tested rules.
- Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
- Look for parameters with command/query metacharacters and unexpected child processes of the service.
Timeline
What happened to this CVE, newest first.
- 2026
- Affected products added · xorbitsai/inference
- SSVC assessment updated
- Record published
- CVSS changed · 8.8
- Source status changed · → Deferred
- Record created in this database
- CVE published
Source activity
Repeated readings are counted rather than listed.
- 1× Official description updated · Oct 13, 2026 – Oct 13, 2026
References
5 on the record
Elsewhere on this site
Related CVEs (same products)
- High CVE-2026-85668 Xinference 3.3.0 Unauthenticated Arbitrary-Path File Read via /v1/models/llm/auto-register Sep 4, 2026
- Critical CVE-2026-61539 Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing Aug 21, 2026
Not in any source we poll
Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.
- No fixed version, patch or mitigation documented.
- No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
- No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
- No exploit packet captures, log samples, or incident case IDs supplied.
Answered from this record
Text assembled only from the fields above — no additional claims.
What should defenders know first?
CVE-2026-76841 is "Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders", rated High. It affects Inference (Xorbitsai); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 8.8 describes technical severity. EPSS 1.03% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.
Comments
Moderated technical discussion. Read the community guidelines.
No comments yet.
Sign in or create an account to comment and suggest corrections.