CVE-2026-61539
Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing
- State
- Published
- Severity
- 10.0 Critical
- Published
- Aug 21, 2026
- Updated
- Aug 24, 2026
- Reserved
- Jul 10, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 10.0 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H | GitHub_M |
Weaknesses
- CWE-95 Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
Affected Products
| Product | Versions |
|---|---|
inferencexorbitsai |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.