{"answers":{"affected":"","exploited":"There is no known exploitation of CVE-2026-76841 in the wild and no public exploit code.","fix":"No fix has been published for CVE-2026-76841 yet. Limit exposure of the affected software until one is available.","what":"CVE-2026-76841 is a high-severity code injection vulnerability in xorbitsai inference, published on 24 Aug 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-76841 and fix it if it is affected.\n\nWhat it is: CVE-2026-76841 is a high-severity code injection vulnerability in xorbitsai inference, published on 24 Aug 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-76841 in the wild and no public exploit code.\n\nAffected product: xorbitsai inference. No package-level version data is available, so check the vendor advisory linked from the reference page.\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-76841/ (Markdown: https://insights.sbomify.com/CVE-2026-76841/index.md)","id":"CVE-2026-76841","markdown":"https://insights.sbomify.com/CVE-2026-76841/index.md","name":"CVE-2026-76841","record":{"aliases":["GHSA-9cx2-fwcj-qq73"],"analysis":{"component_type":"server_software","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"AI inference server","requires_auth":"low_privilege","summary":"Attackers with model launch access can execute arbitrary code by registering malicious models, as the server unconditionally enables remote code execution in model loaders.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"VulnCheck","cpe":[],"cvss":{"score":8.7,"severity":"high","source":"cna","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","version":"4.0"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"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.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":false,"headline":"Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders","id":"CVE-2026-76841","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":0,"n_references":5,"next":{"headline":"Mercado Pago Node.js SDK through 3.4.0 Path Injection via Unencoded Identifiers in Payment Clients","id":"CVE-2026-76842"},"packages":[],"prev":{"headline":"RustDesk through 1.4.9 Heap Buffer Overflow via Unvalidated CLIPRDR FileContentsResponse Length","id":"CVE-2026-76840"},"products":["inference"],"published":"2026-08-24","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-10-01","vendors":["xorbitsai"]},"summary":"Attackers with model launch access can execute arbitrary code by registering malicious models, as the server unconditionally enables remote code execution in model loaders.","url":"https://insights.sbomify.com/CVE-2026-76841/"}