CVE-2026-59822
Act now ● On CISA KEV — actively exploited
Actively exploited — on the CISA KEV list.
CVSS base
8.2
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
EPSS — probability of exploitation (30 days)
0.9%
57.2th percentile
CISA KEV
Listed
Added 2026-09-02 · patch by 2026-09-16
Weakness / dates
CWE-287
Published 2026-07-08 · modified 2026-09-03
CVSS breakdown
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
| Attack Vector | N | Network |
| Attack Complexity | L | Low |
| Privileges Required | N | None |
| User Interaction | N | None |
| Scope | U | Unchanged |
| Confidentiality | H | High |
| Integrity | L | Low |
| Availability | N | None |
Timeline
- 2026-07-08 — Published (NVD)
- 2026-09-02 — Added to CISA KEV (actively exploited)
- 2026-09-16 — CISA patch-by deadline
- 2026-09-03 — Last modified (NVD)
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.
Affected
References
- https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c
- https://github.com/BerriAI/litellm/pull/26463
- https://github.com/BerriAI/litellm/releases/tag/v1.84.0
- https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q
- https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822
- https://www.wiz.io/blog/ai-infrastructure-honeypot