CVE-2026-59819: CWE-73: External Control of File Name or Path in BerriAI litellm
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.10-stable, LiteLLM's /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params, allowing a proxy administrator or another privileged caller with permission to test model connections to read files from the local filesystem via an oidc/file/ reference. This issue is fixed in version 1.83.10-stable.
AI Analysis
Technical Summary
LiteLLM, a proxy server for calling LLM APIs, had an external control of file name or path vulnerability (CWE-73) in its /health/test_connection endpoint. Before version 1.83.10-stable, this endpoint resolved environment and OIDC file references supplied in litellm_params, enabling privileged users with permission to test model connections to read arbitrary local files via oidc/file/ references. The vulnerability is addressed in version 1.83.10-stable.
Potential Impact
An attacker with privileged access to test model connections could read arbitrary files from the local filesystem, potentially exposing sensitive information. The CVSS 4.0 base score is 2.1, indicating low severity with network attack vector, low complexity, and required privileges.
Mitigation Recommendations
Upgrade to LiteLLM version 1.83.10-stable or later, where this vulnerability is fixed. No other mitigation guidance is provided. Patch status is confirmed fixed in 1.83.10-stable.
CVE-2026-59819: CWE-73: External Control of File Name or Path in BerriAI litellm
Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.10-stable, LiteLLM's /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params, allowing a proxy administrator or another privileged caller with permission to test model connections to read files from the local filesystem via an oidc/file/ reference. This issue is fixed in version 1.83.10-stable.
CVSS v4.0
Score 2.1low
Affected software
pkg:github/berriai/litellmRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
LiteLLM, a proxy server for calling LLM APIs, had an external control of file name or path vulnerability (CWE-73) in its /health/test_connection endpoint. Before version 1.83.10-stable, this endpoint resolved environment and OIDC file references supplied in litellm_params, enabling privileged users with permission to test model connections to read arbitrary local files via oidc/file/ references. The vulnerability is addressed in version 1.83.10-stable.
Potential Impact
An attacker with privileged access to test model connections could read arbitrary files from the local filesystem, potentially exposing sensitive information. The CVSS 4.0 base score is 2.1, indicating low severity with network attack vector, low complexity, and required privileges.
Mitigation Recommendations
Upgrade to LiteLLM version 1.83.10-stable or later, where this vulnerability is fixed. No other mitigation guidance is provided. Patch status is confirmed fixed in 1.83.10-stable.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-07-07T15:00:50.978Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a4ea889c9d9e3dbe3a52694
Added to database: 07/08/2026, 19:44:09 UTC
Last enriched: 07/16/2026, 10:06:09 UTC
Last updated: 08/22/2026, 10:52:10 UTC
Views: 73
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.