PoC Monitor
← All CVEs
CVE-2026-61539published 21 Aug 2026 20:37 UTCData: JSON · API

Xorbitsai inference

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

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.

First public PoC None yetno public PoC found
Public PoCs00 on GitHub
CVSS10.0critical · scored by CNA · CWE-95
CISA KEV Not listednot known exploited

Affected versions and mitigation

From the CVE record and the vendor's references.

Affected

xorbitsai inference
  • < 2.7.0

Fixed in 2.7.0

Timeline

Days relative to CVE publication
-2t=0+2+4+6+8CVE published21 Aug 2026 · t = 0

No public PoC found yet; not in CISA KEV.

PoC repositories

Found on GitHub.

No PoC repositories found yet.