CVE-2026-35030
Impersonation via JWT cache collision in LiteLLM when JWT enabled.
Is CVE-2026-35030 being exploited?
Not confirmed. CVE-2026-35030 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 0.63% probability of exploitation in the next 30 days.
How severe is CVE-2026-35030?
CVE-2026-35030 is rated Critical with a CVSS score of 9.4. 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-2026-35030?
Yes. A fix has been recorded for CVE-2026-35030. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-35030 affect?
CVE-2026-35030 affects LiteLLM AI Gateway (JWT/OIDC enabled). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-35030?
Upgrade to v1.83.0+
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Attacker can impersonate a legitimate user and access their permissions via cache hit using crafted token.
Patch when possible
- affected< 1.83.0
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.