Public mode

No access to your tenant or devices. Every item links to its source. What this means

Sources need attention Customize Public modeDiscuss ChangeIntel on Discord

Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing

CVSS 3.1 10.0 CRITICALCheck source for fixed versionsKEV status unknown

cve-program · CVE-2026-61539

Published

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.

Read the publisher's advisory

Affected versions, risk and source history

cve-program · CVE-2026-61539

Published

inference

Vendor product

Publisher's version information

Shown as published. These rules are not interpreted as NuGet package version ranges.

{
                    "vendor": "xorbitsai",
                    "product": "inference",
                    "versions": [
                        {
                            "version": "< 2.7.0",
                            "status": "affected"
                        }
                    ]
                }

Original source record · Cite this exact observation · Complete original publisher JSON

ChangeIntel

An IT change radar: releases, security, known issues, retirements, documentation changes, and service status from public sources. Every item links to supporting evidence; dates and statuses can change after they are read.

Sources read 21 Nov 00:19 UTC · 274 of 275 readable · 270 fully read · documentation 469/469 current