CVE-2026-61539Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing
Updated under an hour ago ()
Does this affect you?
It affects xorbitsai inference. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
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
- 10.0 CRITICAL (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
- Weakness (CWE)
- CWE-95
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- GitHub_M
- NVD analysis
- Deferred
- Record last updated
- Aug 24, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
xorbitsai inference xorbitsai:inference (from the name) | before 2.7.0 | CNA record |
References
- https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9mx-refsource-confirm
- https://github.com/xorbitsai/inference/pull/4786x-refsource-misc
- https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42x-refsource-misc
- https://github.com/xorbitsai/inference/releases/tag/v2.7.0x-refsource-misc
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.