Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing (CVE-2026-61539) | HOL Guard CVE

Unknown severity · Source severity not reportedCVE-2026-61539

Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Answer in brief

CVE-2026-61539 records a Unknown severity vulnerability in Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing. The current sources do not mark it as known exploited. The current feed maps xorbitsai/inference (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Aug 21, 2026Updated Aug 21, 2026Source checked Aug 21, 2026First seen by HOL Aug 21, 2026Material review Aug 21, 2026

Upstream Advisory

Key facts

Risk: Unknown severitySource severity not reported
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Not reported

Why this deserves its current priority

A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps xorbitsai/inference (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
xorbitsai/inferencegeneric	< 2.7.0	Not reported

Recommended response

Check inventory. Check lockfiles and deployed manifests for xorbitsai/inference.
Review the reported fix. Monitor this advisory for an available fix and review any installs of the affected package.

Evidence timeline and material changes

Published upstream
Aug 21, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Aug 21, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Aug 21, 2026

Sources and claim methodology

Upstream source 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.

Quoted source text, attributed separately from HOL analysis.