CVE-2026-59822: BerriAI litellm · Improper Authentication
Affects BerriAI litellmSource CVE Database V5
Exploited in the wild · KEV due 16 Sep 2026 : upgrade to 1.84.0 now.
Data as of 21 Nov 2026, 17:35 UTC
- KEV deadline
- US federal agencies must patch by this date; a sensible deadline for everyone else. Other KEV due dates
- EPSS
- 0.8% chance of exploitation in 30 days – higher than 58% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 1.84.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:NExploitation evidence
t = 0 is the CVE’s publication on cve.org
Disclosed: evidence found.
CVE published 8 Jul 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
Public exploit code: GitHub proofs of concept
Exploited in the wildExploited: evidence found.
Listed in CISA KEV 56 days after disclosure
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
Timeline
CVE ID reserved
by GitHub, Inc.
, 29 hours before disclosure
CVE published
on cve.org
, t = 0
In Threat Radar
record ingested
, 12 minutes after disclosure
Added to CISA KEV (opens in a new tab)
exploitation confirmed
, 56 days after disclosure
KEV remediation due
US federal deadline
, 70 days after disclosure
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), GitHub proofs of concept, CISA KEV (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 21 Nov 2026.
What to do
Upgrade litellm and berriai/litellm to 1.84.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| BerriAIlitellm | Affected
| Fixed in
|
GitHubberriai/litellmpkg:github/berriai/litellmOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
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.
References
- github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q (opens in a new tab)
- github.com/BerriAI/litellm/pull/26463 (opens in a new tab)
- github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c (opens in a new tab)
- github.com/BerriAI/litellm/releases/tag/v1.84.0 (opens in a new tab)
- wiz.io/blog/ai-infrastructure-honeypot (opens in a new tab)
- cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822 (opens in a new tab)