Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…

CVE-2026-59821: CWE-94: Improper Control of Generation of Code ('Code Injection') in BerriAI litellm

0
Low
VulnerabilityCVE-2026-59821cvecve-2026-59821cwe-94
Published: 07/08/2026 (07/08/2026, 19:14:13 UTC)
Source: CVE Database V5
Vendor/Project: BerriAI
Product: litellm

Description

CVE-2026-59821 is a code injection vulnerability in BerriAI's LiteLLM proxy server prior to version 1.82.0-stable. The issue arises because the Custom Code Guardrails create and update endpoints did not enforce the same sandboxing and validation as the test endpoint, allowing privileged users to submit custom Python code that executes within the LiteLLM proxy environment. This could potentially expose secrets accessible to the process. The vulnerability is fixed in version 1.82.0-stable.

CVSS v4.0

Score 2.1low

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
Present
Privileges Required
High
User Interaction
None
Vuln. Confidentiality
Low
Vuln. Integrity
Low
Vuln. Availability
Low
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N

Affected software

GitHub Actionsmore threats →ai
berriai/litellm
pkg:github/berriai/litellm
Affected versions
<1.82.0

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 07/08/2026, 19:58:54 UTC

Technical Analysis

LiteLLM, a proxy server for calling LLM APIs, had a vulnerability in its Custom Code Guardrails production create and update paths before version 1.82.0-stable. These paths lacked the sandboxing and validation protections present in the test endpoint, enabling a privileged user with access to create or update guardrails to inject and execute arbitrary Python code within the proxy environment. This improper control of code generation (CWE-94) could lead to exposure of secrets available to the process. The issue is resolved in version 1.82.0-stable.

Potential Impact

A privileged user with access to create or update Custom Code Guardrails could execute arbitrary Python code in the LiteLLM proxy environment, potentially exposing sensitive secrets accessible to the process. The CVSS score is low (2.1), reflecting the requirement for privileged access and limited scope of impact.

Mitigation Recommendations

Upgrade to LiteLLM version 1.82.0-stable or later, where this vulnerability is fixed. No official patch advisory is provided, but the fix is included in the stated version. Until upgrading, restrict privileged user access to the Custom Code Guardrails create and update functionality to trusted personnel only.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

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: 6a4ea889c9d9e3dbe3a526a0

Added to database: 07/08/2026, 19:44:09 UTC

Last enriched: 07/08/2026, 19:58:54 UTC

Last updated: 07/08/2026, 20:20:59 UTC

Views: 4

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

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

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses