CVE-2026-59821

HIGH EXPLOITED

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

Title source: cna
STIX 2.1

Exploitation Summary

CVE-2026-59821 has been observed exploited in the wild (reported by VulnCheck KEV).

Description

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable.

References (3)

Core 3

Scores

CVSS v3 7.2
EPSS 0.0036
EPSS Percentile 28.2%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment
Exploitation none
Automatable no
Technical Impact partial

Details

VulnCheck KEV 2026-07-26
CWE
CWE-94
Status published
Products (4)
BerriAI/litellm < 1.82.0-stable
litellm/litellm 1.82.0 nightly
litellm/litellm < 1.82.0
pypi/litellm 0 - 1.82.0PyPI
Published Jul 08, 2026
Tracked Since Jul 09, 2026