BerriAI · LiteLLM · published 2026-07-08
CVE-2026-59821LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
Routine No exploitation evidence; EPSS 0.9%.
CVE-2026-59821 is not known to be exploited in the wild. EPSS estimates a 0.9% chance of exploitation in the next 30 days, higher than 60% of all CVEs. This LiteLLM vulnerability: CVSS 2.1 (v4.0). Fixed upstream in LiteLLM 1.84.0, 1.83.10-stable, 1.83.7-stable, 1.82.0-stable. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in LiteLLM 1.84.0, 1.83.10-stable, 1.83.7-stable, 1.82.0-stable.
Patch events
AI toolingLiteLLM
LiteLLM security releases: 1.84.0, 1.83.10-stable, 1.83.7-stable, 1.82.0-stable
Upgrade to
1.84.01.83.10-stable1.83.7-stable1.82.0-stableWhy: CVE-2026-59822: Known exploited server software, exploitation is automatable.
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.9% (61th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 2.1 (v4.0)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 | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- BerriAI litellm
< 1.82.0-stable(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.