CVE-2026-59822
Auth bypass in LiteLLM (<1.84.0) lets unauthenticated requests reach MCP backend.
Is CVE-2026-59822 being exploited?
Yes. CVE-2026-59822 appears in CISA's Known Exploited Vulnerabilities catalog, which means exploitation in the wild has been confirmed and reported. Treat it as active rather than theoretical, and patch it ahead of higher-scoring vulnerabilities that carry no exploitation evidence.
How severe is CVE-2026-59822?
CVE-2026-59822 is rated High with a CVSS score of 8.8. 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-2026-59822?
Yes. A fix has been recorded for CVE-2026-59822. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-59822 affect?
CVE-2026-59822 affects LiteLLM < 1.84.0, MCP Streamable HTTP endpoint, AI gateway/proxy deployments using LiteLLM. Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-59822?
Upgrade to LiteLLM 1.84.0+; block/validate malformed Authorization headers at edge.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Unauthenticated attackers can bypass API key validation via crafted Authorization header to invoke MCP tooling, enabling unauthorized API calls and potential data access/actions.
Immediate action required
- affected< 1.84.0
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.