CVE-2026-59822: BerriAI LiteLLM exploited

Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.

What it is

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.

Description quoted from the CVE record (assigned by GitHub_M, published 2026-07-08).

Weakness: CWE-287: Improper Authentication; CWE-306: Missing Authentication for Critical Function

How it can be exploited

Exploitable over the network with low attack complexity with no special attack requirements needing no privileges and no user interaction. Impact: confidentiality high, integrity low, availability none. 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

CISA assessment (SSVC): CISA assesses exploitation as active. Automatable: yes. Technical impact: partial.

On CISA KEV since: 2026-09-02
US federal deadline: 2026-09-16
Ransomware use: Not known

Public exploit evidence (Exploit Observer)

Also known as: EUVD-2026-42359, GHSA-7488-6r32-c95q

VEDAS cluster: VEDAS:BARNACLEBEAR

Exploit Observer links 5 pieces of public exploit code or detection modules that name this CVE or one of its aliases.

Exploit code and modules (5)

Code that names this CVE. A repository can be a working exploit, a scanner, a fake or malware; read it before running anything.

Vulnerability databases and vendor advisories (6)

Catalogue entries, not exploit evidence.

Vulnerability database or vendor advisory: https://euvd.enisa.europa.eu/enisa/EUVD-2026-42359
Vulnerability database or vendor advisory: https://github.com/advisories/GHSA-7488-6r32-c95q
Vulnerability database or vendor advisory: https://nvd.nist.gov/vuln/detail/CVE-2026-59822
Vulnerability database or vendor advisory: https://osv.dev/vulnerability/CVE-2026-59822
Vulnerability database or vendor advisory: https://osv.dev/vulnerability/GHSA-7488-6r32-c95q
Vulnerability database or vendor advisory: https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822

News (1)

News: https://www.techgines.com/post/litellm-mcp-authentication-bypass-cve-2026-59822

153 more references returned by Exploit Observer did not name this CVE or an alias, so they are left out.

VEDAS data as of 2026-11-01T17:12 UTC; fetched 2026-11-02.

Live scores

EPSS: 0.008
low predicted chance of attack
VEDAS: 0.988
strong exploit evidence
On CISA KEV: Yes, since 2026-09-02
Detection rule: Nuclei · Suricata

EPSS (chance of attack)

VEDAS (exploit evidence)

Thin horizontal line: the “likely” (EPSS 0.10) or “strong” (VEDAS 0.90) threshold. Shaded “no data” areas are periods when cve-scores did not publish. The vertical line is the day CISA added it to its exploited list.

VEDAS flagged this bug about 12 days before CISA confirmed attacks.

Who is affected

Product	Affected	Not affected
BerriAI litellm	version < 1.84.0	Not stated

Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.

Exploit Observer also maps it to: litellm litellm, pypi litellm.

How to fix it

CISA required action: Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset’s internet exposure and ensuring adherence to BOD 26-04 patching guidelines.

Vendor guidance:

How to detect it

Nuclei template (active check)

LiteLLM - MCP Authentication Bypass via OAuth2 Passthrough Fallback
LiteLLM (AI Gateway) before 1.84.0 exposes an MCP Streamable HTTP endpoint at /mcp/. When a request carries a fabricated Authorization header, failed LiteLLM key validation falls through an OAuth2 passthrough path that substitutes an empty UserAPIKeyAuth() object, so the request reaches MCP tooling without a valid LiteLLM key. An unauthenticated attacker can complete the MCP initialize handshake and invoke tools.

Name and description quoted from the template, written by VEDAS.

The template sends 1 request (POST /mcp/); it decides using dsl matchers. Severity in the template: high. Marked as not yet verified against a live vulnerable target.

Run it against a host you own or are authorised to test:

bash

nuclei -u https://your-host -t CVE-2026-59822.yaml

Show the template (40 lines)

yaml

id: CVE-2026-59822

info:
  name: "LiteLLM - MCP Authentication Bypass via OAuth2 Passthrough Fallback"
  author: vedas-arpsyndicate
  severity: high
  description: |
    LiteLLM (AI Gateway) before 1.84.0 exposes an MCP Streamable HTTP endpoint at /mcp/.
    When a request carries a fabricated Authorization header, failed LiteLLM key validation
    falls through an OAuth2 passthrough path that substitutes an empty UserAPIKeyAuth()
    object, so the request reaches MCP tooling without a valid LiteLLM key. An
    unauthenticated attacker can complete the MCP initialize handshake and invoke tools.
  reference:
    - https://www.exploit.observer/?keyword=CVE-2026-59822&match=exact
    - https://subdomain.center/?engine=ammonites&keyword=litellm&match=exact
  classification:
    cvss-metrics: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:L/SI:L/SA:L
    cve-id: CVE-2026-59822
    cwe-id: CWE-287
  metadata:
    verified: false
  tags: cve,cve2026,litellm,mcp,auth-bypass
http:
  - raw:
      - |
        POST /mcp/ HTTP/1.1
        Host: {{Hostname}}
        Content-Type: application/json
        Accept: application/json, text/event-stream
        Authorization: Bearer sk-{{randstr}}

        {"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"mcp","version":"1.0"}}}

    matchers:
      - type: dsl
        dsl:
          - 'contains(body, "protocolVersion")'
          - 'contains(body, "jsonrpc")'
          - 'status_code == 200'
        condition: and

CVE-2026-59822.yaml on GitHub

Suricata rules (network detection)

1 rule that alert on traffic matching this exploit: VEDAS CVE-2026-59822 LiteLLM - MCP Authentication Bypass Attempt. Add them to your Suricata rule set and reload.

Show the rules

suricata

alert http $EXTERNAL_NET any -> $HOME_NET any (msg:"VEDAS CVE-2026-59822 LiteLLM - MCP Authentication Bypass Attempt"; flow:established,to_server; http.method; content:"POST"; http.uri; content:"/mcp"; nocase; http.request_body; content:"initialize"; nocase; fast_pattern; content:"jsonrpc"; nocase; classtype:web-application-attack; reference:cve,CVE-2026-59822; reference:url,https://www.exploit.observer/?keyword=CVE-2026-59822&match=exact; reference:url,https://subdomain.center/?engine=ammonites&keyword=litellm&match=exact; sid:1081400; rev:1;)

CVE-2026-59822.rules on GitHub

References

Other databases

Where this comes from

This advisory is generated automatically by VEDAS from: CVE.org record, CISA KEV, cve-scores (EPSS and VEDAS), Exploit Observer, vedas-signatures. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.