CRITICAL

CVE-2026-61539

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

CVSS v3

CRITICAL

EPSS Score

1.2 %

exploit probability, as of 2026-09-25

CISA KEV

known exploited

Exploitation

—

SSVC status

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

Technical details

Published: 2026-08-21
Last Modified: 2026-08-21

Frequently asked questions

What is CVE-2026-61539?

Is CVE-2026-61539 actively exploited?

Active exploitation of CVE-2026-61539 has not been confirmed. Its EPSS score was 1.2% on 2026-09-25, the estimated probability of exploitation in the next 30 days.

What is the CVSS score for CVE-2026-61539?

CVE-2026-61539 has a CVSS v3 base score of 10 (CRITICAL severity).

Is CVE-2026-61539 affecting your environment?

Use isMalicious to check if any of your IPs or domains are associated with this vulnerability's IOCs.

Check an IP Search CVEs SIEM & TIP integrations

No credit card required · 500 free checks/month · Free API key

Other 2026 vulnerabilities worth triaging

Ranked by exploit probability (EPSS).

Back to CVE Database