CVE-2026-61539

critical

Assigned by CNA: github_m

Published 2026-08-21 · Modified 2026-08-21

Discuss on Community Propose mitigation

CVSS v3

10.0

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

CVSS v4 NEW

—

not yet in upstream

VIR risk

10.0

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.

Predictions

Exploit likelihood

98%

Patch ETA

—

Heuristic predictions, AS-IS, for prioritization only.

Mitigations

No mitigations published for this CVE yet.

The vendor-content worker queues fetches as references arrive (check back in a few minutes). Or — if you've already worked around this in production — publish your fix to the community-verified tier.

Propose a mitigation on Community Mitigations published via the community go through AI scoring + 2 human reviewers + 7-day silent objection window before landing here with source_tier=community-verified.

References

CWEs

CWE-95

Community-verified mitigations for this CVE will appear above when contributors publish them.

Verify integrity in audit chain (admin only). AS-IS.