How severe is CVE-2026-59822?

CVE-2026-59822 has a CVSS 3.x base score of 8.2, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity low, and availability none.

Is CVE-2026-59822 being actively exploited?

Yes. CVE-2026-59822 is on CISA's Known Exploited Vulnerabilities (KEV) catalog, added on 2026-09-02, which means active exploitation has been confirmed. It should be prioritised for remediation.

What products are affected by CVE-2026-59822?

CVE-2026-59822 affects Litellm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-59822?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Because this CVE is known to be actively exploited, treat remediation as urgent — CISA KEV typically sets a short remediation deadline.

When was CVE-2026-59822 published?

CVE-2026-59822 was published on 2026-07-08 and last updated on 2026-09-03.

CVE-2026-59822

CVE-2026-59822 is a high-severity vulnerability in Litellm with a CVSS 3.x base score of 8.2. It is listed in CISA's Known Exploited Vulnerabilities (KEV) catalog, confirming it has been exploited in the wild (added 2026-09-02). The underlying weakness is classified as CWE-287.

Key facts

Severity: High (CVSS 3.x base score 8.2)
CVSS v4: 8.8
EPSS exploit prediction: 1% (57th percentile)
Actively exploited: Yes — listed in CISA KEV (added 2026-09-02)
Weakness: CWE-287
Affected product: Litellm
Published: 2026-07-08
Last modified: 2026-09-03

Description

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.

Frequently asked questions

What is CVE-2026-59822?: LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.
How severe is CVE-2026-59822?: CVE-2026-59822 has a CVSS 3.x base score of 8.2, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity low, and availability none.
Is CVE-2026-59822 being actively exploited?: Yes. CVE-2026-59822 is on CISA's Known Exploited Vulnerabilities (KEV) catalog, added on 2026-09-02, which means active exploitation has been confirmed. It should be prioritised for remediation.
What products are affected by CVE-2026-59822?: CVE-2026-59822 affects Litellm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-59822?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Because this CVE is known to be actively exploited, treat remediation as urgent — CISA KEV typically sets a short remediation deadline.
When was CVE-2026-59822 published?: CVE-2026-59822 was published on 2026-07-08 and last updated on 2026-09-03.

References

Affected products (1)

cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*

More vulnerabilities in Litellm

CVE-2026-49468 — Critical (CVSS 9.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, a Host-header…
CVE-2026-42208 — Critical (CVSS 9.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before…
CVE-2024-5751 — Critical (CVSS 9.8): BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The…
CVE-2024-2952 — Critical (CVSS 9.8): BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The…
CVE-2026-35030 — Critical (CVSS 9.1): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, when JWT…
CVE-2026-47102 — High (CVSS 8.8): LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint. While the endpoint…

All CVEs affecting Litellm →

Other CWE-287 (Improper Authentication) vulnerabilities

CVE-2026-83099 — Critical (CVSS 10.0): Vulnerability in the Oracle Forms product of Oracle Fusion Middleware (component: Forms Services, C/S, Charmode).…
CVE-2026-83059 — Critical (CVSS 10.0): Vulnerability in the Oracle Internet Directory product of Oracle Fusion Middleware (component: OID LDAP Server).…
CVE-2026-83021 — Critical (CVSS 10.0): Vulnerability in the Oracle WebLogic Server product of Oracle Fusion Middleware (component: Web Container). Supported…
CVE-2026-83020 — Critical (CVSS 10.0): Vulnerability in the Oracle Platform Security for Java product of Oracle Fusion Middleware (component: Centralized…
CVE-2026-71133 — Critical (CVSS 10.0): Vulnerability in the Oracle Access Manager product of Oracle Fusion Middleware (component: Authentication Engine).…
CVE-2026-76658 — Critical (CVSS 10.0): A vulnerability has been identified in the SSH daemon of HPE Networking Fabric Composer that could allow an…

Browse all CWE-287 (Improper Authentication) vulnerabilities →