Skip to content
CriticalVulnerabilityLLM-specific

GHSA-x2rj-828p-hx9m: Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Published
Record updated
View JSON
Affected
  • xinference <= 2.5.0
Fixed in
2.7.0
  • released April 25, 2026, 118 days before disclosure
Known exploitation
Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS
1.2%

Summary

Xinference used Python's eval() to parse Llama3 tool-call output in the extract_tool_calls() function of xinference/model/llm/tool_parsers/llama3_tool_parser.py. A remote, unauthenticated attacker can use prompts sent to the /v1/chat/completions endpoint to make the model return a Python expression, which the server evaluates. The flaw is rated Critical, CVSS 10.0, and allows remote code execution in the Xinference server process in the tested default deployment.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.