Detections
Analytics

SCA: security update for xinference (GHSA-x2rj-828p-hx9m)

critical Tenable Self-Hosted Container Security Plugin ID 446213

Description

There are packages installed that are affected by a vulnerability referenced in the following CVE:

 - 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. (CVE-2026-61539)

Solution

Update the xinference library and its related packages to version 2.7.0 or later.

See Also

https://github.com/advisories/GHSA-x2rj-828p-hx9m

Plugin Details

Severity: Critical

ID: 446213

Version: Revision 1.1

Type: Local

Family: SCA Checks

Published: 8/22/2026

Updated: 8/22/2026

Risk Information

Vendor

Vendor Severity: Critical

CVSS v2

Risk Factor: Critical

Base Score: 10

Temporal Score: 7.4

Vector: CVSS2#AV:N/AC:L/Au:N/C:C/I:C/A:C

CVSS Score Source: CVE-2026-61539

CVSS v3

Risk Factor: Critical

Base Score: 10

Temporal Score: 8.7

Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Temporal Vector: CVSS:3.0/E:U/RL:O/RC:C

Vulnerability Information

Exploit Ease: No known exploits are available

Patch Publication Date: 8/21/2026

Vulnerability Publication Date: 8/21/2026

Reference Information

CVE: CVE-2026-61539

cwe: CWE-95