Threat database

Xinference through 4.0.1 contains a path traversal vulnerability on Windows that allows unauthenticated attackers to write and delete arbitrary .json files via backslash sequences in model_name. Attackers can register a persisted custom model through POST /v1/model_registrations/{model_type} with names like ..\..\evil to overwrite configuration or data files writable by the Xinference process.

Xorbits Xoscar versions 0.1.0 through 0.11.2 contain an unauthenticated deserialization vulnerability. This flaw allows remote attackers to execute arbitrary code by sending specially crafted data over the actor-pool TCP channel. The vulnerability arises because the server uses cloudpickle.loads() on unvalidated data received via SocketChannel.recv(), triggering execution of pickle __reduce__ gadgets before message type validation. This can lead to remote code execution with the privileges of the server process, which often runs as root on GPU nodes.

Xinference (affected commit 4a94832, v3.x) contains an unauthenticated arbitrary-path file read vulnerability in the POST /v1/models/llm/auto-register endpoint, which accepts a caller-supplied model_path parameter without authentication or path confinement. The endpoint reads and parses config.json, tokenizer_config.json, and chat_template.jinja files at the supplied path and reflects the parsed content back to the caller, allowing an unauthenticated attacker to probe the server filesystem and extract content of files with those names in any directory.

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.

CVE-2026-61539 is a critical remote code execution vulnerability in xorbitsai inference API versions 2.5.0 and earlier. The vulnerability arises from improper neutralization of directives in dynamically evaluated code (eval injection) where attacker-controlled input is passed to Python's eval() function. An unauthenticated attacker can exploit this by crafting malicious prompts to execute arbitrary commands on the Xinference server. The issue is fixed in version 2.7.0.