CVE-2026-12773 json
BerriAI litellm MCP Proxy user_api_key_auth_mcp.py UserAPIKeyAuth improper authentication
published 2026-06-21 4 mo ago modified 2026-10-25 14 d ago also GHSA-4jcj-7x88-m979 , PYSEC-2026-4067 , EUVD-2026-38139
- cvss
- 7.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.0%
- EPSS 1.0% chance of exploitation in 30 days, percentile 63%
- public exploits
- 0
- none known
Summary
A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be launched remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure.
Patch / fix
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-12773 updated cvss 7.3
litellm: BerriAI litellm: Improper authentication in MCP Proxy via UserAPIKeyAuth function
-
Red Hat Exploit Intelligence exploit-intelligence/vulnerability-analysis-rhel9, exploit-intelligence-tech-preview/vulnerability-analysis-rhel9affected: workaround, no fix available “Upgrade to litellm 1.81.16 or later. As a workaround, do not configure backend MCP servers with allow_all_keys: true, and restrict network access to the LiteLLM MCP proxy endpoints.”
-
Red Hat Ansible Automation Platform 2 ansible-automation-platform-26/lightspeed-chatbot-rhel9, ansible-automation-platform-27/lightspeed-chatbot-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-mlflow-rhel9, rhoai/odh-llama-stack-core-rhel9, rhoai/odh-th-torch-cpu-py312-rhel9, rhoai/odh-th-torch-cuda-py312-rhel9, rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9not affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 4 mo ago
Exploit prediction
1.02% chance of exploitation in the next 30 days, higher than 63% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- vuldb.com https://vuldb.com/submit/811282 referenced PoC, tagged "exploit" by a source, unverified
- gist.github.com https://gist.github.com/YLChen-007/3cfaad10a69d7a15e4d4d458cb53309e referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.9 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P |
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R |
| CNA | 3.0 | 7.3 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P/E:POC/RL:ND/RC:UR |
| CISA ADP | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| CNA | 4.0 | 5.5 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| NVD | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P |
| GitHub | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| OSV | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | litellm | <1.84.0 |
1.84.0 |
Affected products
- BerriAI litellm
- Red Hat Exploit Intelligence
- Red Hat Red Hat Ansible Automation Platform 2
- Red Hat Red Hat OpenShift AI (RHOAI)
Classification
References
-
github.com
/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c
web
-
vuldb.com
/submit/811282
third-party-advisory, exploit, web, vdb-entry
-
gist.github.com
/YLChen-007/3cfaad10a69d7a15e4d4d458cb53309e
exploit, web, third-party-advisory
-
vuldb.com
/vuln/372515
vdb-entry, technical-description, web, third-party-advisory
-
vuldb.com
/vuln/372515/cti
signature, permissions-required, web, vdb-entry
-
vuldb.com
/cve/CVE-2026-12773
third-party-advisory, web, vdb-entry
-
access.redhat.com
/security/cve/CVE-2026-12773
vdb-entry, web
-
bugzilla.redhat.com
/show_bug.cgi?id=2491112
issue-tracking, web
-
security.access.redhat.com
/data/csaf/v2/vex/2026/cve-2026-12773.json
web
-
nvd.nist.gov
/vuln/detail/CVE-2026-12773
advisory
-
github.com
/BerriAI/litellm
package
-
pypi.org
/project/litellm
package
-
github.com
/advisories/GHSA-4jcj-7x88-m979
advisory
Sources
- CVE List CVE-2026-12773
- GitHub Advisory GHSA-4jcj-7x88-m979
- NVD CVE-2026-12773
- OSV PYSEC-2026-4067
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.