CVE-2026-61539 — CRITICAL (10.0)

Vulnerability Description

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.

CVSS Score

10.0

CRITICAL

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Attack Vector

NETWORK

Attack Complexity

LOW

Privileges Required

NONE

User Interaction

NONE

Scope

CHANGED

Confidentiality

HIGH

Integrity

HIGH

Availability

HIGH

Related Weaknesses (CWE)

CWE-95

References

FAQ

What is CVE-2026-61539?

CVE-2026-61539 is a vulnerability with a CVSS score of 10.0 (CRITICAL). 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...

How severe is CVE-2026-61539?

CVE-2026-61539 has been rated CRITICAL with a CVSS base score of 10.0/10. This is considered a critical vulnerability requiring immediate attention.

Is there a patch for CVE-2026-61539?

Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.