# CVE-2026-59822 — Litellm

**CISA KEV**

> As of 2026-09-03, CVE-2026-59822 is a HIGH-severity vulnerability in Litellm, CVSS v3.1 8.2, EPSS 0.8% (56.4th percentile). It is listed in the CISA Known Exploited Vulnerabilities catalog (added 2026-09-02), with a US federal remediation deadline of 2026-09-16. Threadlinqs Intelligence links 1 tracked threat campaign to CVE-2026-59822, most recently “Qilin-Linked Campaign Exploits MCP Gateway and LLM Framework Flaws (CVE-2026-59822, CVE-2026-42271, CVE-2026-48710) for RCE and Cryptomining”.

**Last updated:** 2026-09-03

## 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.

The record classifies CVE-2026-59822 under weakness classes [CWE-287](https://intel.threadlinqs.com/cwe/CWE-287), [CWE-306](https://intel.threadlinqs.com/cwe/CWE-306). Its CVSS v3 base vector states that the flaw is reachable remotely over the network, needs no prior authentication, needs no user interaction, and has high impact on confidentiality. 1 affected-product entry is recorded, across 1 vendor, listed below. The identifier was first published 134 days ago.

## Severity and exploitation probability

- **CVSS v3.1 base score:** 8.2 — HIGH (`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N`)
- **CVSS v4.0 base score:** 8.8 (`CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N`)
- **EPSS (FIRST):** 0.8% probability of exploitation in the next 30 days, higher than 56.4% of all scored CVEs
- **CISA KEV:** Listed since 2026-09-02, federal remediation deadline 2026-09-16
- **Threadlinqs priority:** 9/10 — CISA KEV-listed, which Threadlinqs floors at 9
- **Published:** 2026-07-08

## Is CVE-2026-59822 being exploited?

CISA added CVE-2026-59822 to the Known Exploited Vulnerabilities catalog on 2026-09-02, which means the agency holds evidence of exploitation in the wild; US federal civilian agencies had to remediate it by 2026-09-16 under BOD 22-01. Weaponised exploit code for CVE-2026-59822 is publicly available. 2 public proof-of-concept repositories are tracked for this identifier. It currently carries a trending score of 44 in the Threadlinqs vulnerability feed.

- [HORKimhab/CVE-2026-59822](https://github.com/HORKimhab/CVE-2026-59822) (github)
- [trickest/cve](https://github.com/trickest/cve/blob/main/2026/CVE-2026-59822.md) (trickest)

## Affected products and versions

- [BerriAI](https://intel.threadlinqs.com/vendors/berriai): litellm

Affected software packages:

- `pip:litellm` — patched in 1.84.0

## How to fix CVE-2026-59822

The record marks a vendor fix as available for CVE-2026-59822. Fixed versions are recorded for 1 package: pip:litellm 1.84.0. Patch reference: [https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c](https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c). Vendor advisory: [https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q](https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q). Because CVE-2026-59822 is KEV-listed, US federal civilian agencies were required to apply the vendor fix, or stop using the product, by 2026-09-16. Apply the vendor fix referenced above to every affected product listed in this record, then confirm the running version against the vendor advisory.

## Threat activity tracking CVE-2026-59822

1 tracked threat in the Threadlinqs corpus references CVE-2026-59822, either in the campaign’s CVE list or as an indicator on the campaign record.

- [Qilin-Linked Campaign Exploits MCP Gateway and LLM Framework Flaws (CVE-2026-59822, CVE-2026-42271, CVE-2026-48710) for RCE and Cryptomining](https://intel.threadlinqs.com/threat/TL-2026-2185) — CRITICAL · 2026-08-28

## Sources

Enriched from CVE.org, NVD, FIRST EPSS, CISA KEV, GitHub Security Advisories, public proof-of-concept repositories. This product uses the NVD API but is not endorsed or certified by the NVD.

**Vendor advisory and patch**

- [github.com](https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q)

**Other references**

- [github.com](https://github.com/BerriAI/litellm/pull/26463)
- [github.com (73869f0faf7d11ee21adcb5f91b8c33a340b6c2c)](https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c)
- [github.com (v1.84)](https://github.com/BerriAI/litellm/releases/tag/v1.84.0)

Canonical: https://intel.threadlinqs.com/cve/CVE-2026-59822
Every threat comes with one complete detection in Splunk SPL, Microsoft KQL and Sigma, free for everyone; a free account adds daily TL Creds to unlock the rest. Sign up free (Blue): https://threadlinqs.com/?modal=signup
Indicator values unlock with TL Creds (https://threadlinqs.com/tl-creds); MCP access for AI agents needs Purple: https://intel.threadlinqs.com/mcp
