cve.bz

CVE-2026-61539 xorbitsai inference: Eval Injection

10.0 criticalEPSS 1.2%Fix available

Critical (10.0) in xorbitsai inference. EPSS 1.2% estimated probability of exploitation activity in the next 30 days. Fixed in xinference 2.7.0.

On this page
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.

Severity

CVSS 3.1

10.0 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
EPSS
1.2% (unchanged from 1.2% a week ago; 1.2% 30 days ago) estimated probability of exploitation activity in the next 30 days; 69th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: total, assessed 2026-08-24. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-95 Improper Neutralization of Directives in Dynamically Evaluated Code (Eval Injection)
OWASP Top 10
A05:2025 Injection
Published
Modified
NVD analysis
Deferred: the NVD does not plan to analyze it
Record from
the NVD, synced

Fix and patched versions

  • xinference (PyPI): fixed in 2.7.0

Ask an AI about this CVE

Show the promptExplain CVE-2026-61539 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-61539?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-61539?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-61539 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
xorbitsai inference< 2.7.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-x2rj-828p-hx9mPyPIxinference<2.7.02.7.0
PYSEC-2026-3946PyPIxinference<2.7.02.7.0

Attack patterns (CAPEC)

  • CAPEC-35 Leverage Executable Code in Non-Executable Files Likelihood: High · Severity: Very High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON