XorbitsAI Xinference up to 2.6.x Llama3 Tool Parser llama3_tool_parser.py extract_tool_calls Tools code injection

Summaryinfo

A vulnerability categorized as critical has been discovered in XorbitsAI Xinference up to 2.6.x. Impacted is the function extract_tool_calls of the file xinference/model/llm/tool_parsers/llama3_tool_parser.py of the component Llama3 Tool Parser. Executing a manipulation of the argument Tools can lead to code injection. The identification of this vulnerability is CVE-2026-61539. The attack may be launched remotely. There is no exploit available.

Detailsinfo

A vulnerability was found in XorbitsAI Xinference up to 2.6.x. It has been declared as critical. This vulnerability affects the function extract_tool_calls of the file xinference/model/llm/tool_parsers/llama3_tool_parser.py of the component Llama3 Tool Parser. The manipulation of the argument tools with an unknown input leads to a code injection vulnerability. The CWE definition for the vulnerability is CWE-94. The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0.

The advisory is available at github.com. This vulnerability was named CVE-2026-61539 since 07/10/2026. The exploitation appears to be easy. The attack can be initiated remotely. No form of authentication is required for a successful exploitation. Technical details are known, but there is no available exploit. This vulnerability is assigned to T1059 by the MITRE ATT&CK project.

Upgrading to version 2.7.0 eliminates this vulnerability.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Vendor

• XorbitsAI

Name

• Xinference

Version

• 2.0
• 2.1
• 2.2
• 2.3
• 2.4
• 2.5
• 2.6

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion