CVE-2026-61539

Katalog CVE

CVSS 10.0 · Critical EPSS 1,2%

Kerentanan Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection'). Skor CVSS 3.1 10.0 (Critical) menurut github.com.

Deskripsi (NVD)

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.

Rincian

Terbit di NVD

21 Agustus 2026

Terakhir diubah

12 Oktober 2026

Status NVD

Deferred

CVSS 3.1

10.0 (Critical), sumber github.com
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H · uraikan di kalkulator

Jenis kelemahan (CWE)

CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')

EPSS (30 hari)

1,2% peluang dieksploitasi; lebih tinggi dari 68,0% CVE lain

Produk dan versi terdampak

NVD belum mencantumkan data produk (CPE) untuk CVE ini. Produk yang terdampak biasanya disebut di deskripsi dan di advisory vendor pada daftar referensi.

Referensi dan perbaikan

• https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42
• https://github.com/xorbitsai/inference/pull/4786
• https://github.com/xorbitsai/inference/releases/tag/v2.7.0
• https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m