CVE-2026-61539
Unauthenticated remote RCE via model eval in Xinference
Is CVE-2026-61539 being exploited?
Not confirmed. CVE-2026-61539 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.66% probability of exploitation in the next 30 days.
How severe is CVE-2026-61539?
CVE-2026-61539 is rated Critical with a CVSS score of 10.0. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-61539?
Yes. A fix has been recorded for CVE-2026-61539. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-61539 affect?
CVE-2026-61539 affects Xinference <= 2.5.0, Xinference /v1/chat/completions API, Servers running Xinference inference API. Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-61539?
Upgrade to Xinference 2.7.0; block untrusted model inputs and restrict network access.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Unauthenticated attacker can execute arbitrary Python/code in the Xinference server process via crafted prompts.
Immediate action required
- affected< 2.7.0
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.