THREAT OPS › Threat News › [GHSA] GHSA-x2rj-828p-hx9m (critical) — Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing
[GHSA] GHSA-x2rj-828p-hx9m (critical) — Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing
GHSA-x2rj-828p-hx9m Severity: critical CVE: CVE-2026-61539
Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing
### Summary
Xinference used Python's unsafe `eval()` function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API,
MITRE ATT&CK techniques
- Reverse ShellAML.T0072
Indicators of compromise
- CVE-2026-61539cve
- xlabai@tencent.comemail
- wgnbuaa@gmail.comemail
- pkugenuine@gmail.comemail
- lgcpku@gmail.comemail
Original source: https://github.com/advisories/GHSA-x2rj-828p-hx9m