CVE-2026-59822
LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback
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
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.
Official description from the CVE record, published by GitHub_M. Copyright © 1999-2026 The MITRE Corporation. See /security/cve/legal for the CVE license. View the record on cve.org
Key data
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
Attack vector: Network
The vulnerable component can be reached over a network, possibly from the Internet.
Attack complexity: Low
No measurable action is needed to get around the system's built-in security controls. The attack is repeatable.
Attack requirements: None
The attack works without any special deployment or execution conditions.
Privileges required: None
No account or privileges are needed.
User interaction: None
No action from any user is needed.
Vulnerable system: confidentiality: High
Serious or total effect on the secrecy of data.
Vulnerable system: integrity: Low
Limited effect on the trustworthiness of data.
Vulnerable system: availability: None
No effect on availability.
Subsequent systems: confidentiality: None
No effect on other systems' data secrecy.
Subsequent systems: integrity: None
No effect on other systems' data trustworthiness.
Subsequent systems: availability: None
No effect on other systems' availability.
| Metric | Value | What it means |
|---|---|---|
| Attack vector | Network | The vulnerable component can be reached over a network, possibly from the Internet. |
| Attack complexity | Low | No measurable action is needed to get around the system's built-in security controls. The attack is repeatable. |
| Attack requirements | None | The attack works without any special deployment or execution conditions. |
| Privileges required | None | No account or privileges are needed. |
| User interaction | None | No action from any user is needed. |
| Vulnerable system: confidentiality | High | Serious or total effect on the secrecy of data. |
| Vulnerable system: integrity | Low | Limited effect on the trustworthiness of data. |
| Vulnerable system: availability | None | No effect on availability. |
| Subsequent systems: confidentiality | None | No effect on other systems' data secrecy. |
| Subsequent systems: integrity | None | No effect on other systems' data trustworthiness. |
| Subsequent systems: availability | None | No effect on other systems' availability. |
CVSS is owned and managed by FIRST.Org, Inc. (FIRST) and is used by permission. Each CVSS score on this site is shown together with its vector string, as published in the CVE record by the source named next to it. Learn more at first.org/cvss.
- Score
- 0.00836 (0.8% probability)
- Percentile
- 58.0%
- Scores of
- Nov 10, 2026
- Model
- v2026.06.15
- Name in the catalog
- BerriAI LiteLLM Improper Authentication Vulnerability
- Added to the catalog
- Sep 2, 2026
- Federal due date
- Sep 16, 2026
- Exploitation
- Recorded by CISA as active
- Automatable
- yes
- Technical impact
- partial
BerriAI litellm
- affected: < 1.84.0
- github.comx_refsource_CONFIRM
- github.comx_refsource_MISC
- github.comx_refsource_MISC
- github.comx_refsource_MISC
- ID reserved
- Record published
- Added to CISA KEV
- Record last updated
Look up another CVE
Data from the CVE Program (MITRE), CISA KEV and FIRST EPSS. CVSS is owned by FIRST and used by permission. Not affiliated with or endorsed by MITRE, CISA or FIRST. Data as of Nov 10, 2026, 19:07 UTC. Sources and licenses