CVE-2024-4264Public exploitNetwork attack vector

Remote code execution via unsanitized secret evaluation

Published May 18, 2024 · Updated Sep 3, 2024

Code injection in Berri AI LiteLLM 1.28.11 and earlier allows remote attackers to execute arbitrary code through proxy configuration updates. The get_secret() method passes attacker-controlled environment-variable values to Python eval() without sanitization when Google KMS is used. Exploitation requires a proxy deployment using Google KMS and access to /config/update; successful input runs code in the proxy process.

CVSS severity9.8
Critical
EPSS probability0.88%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Code injection in Berri AI LiteLLM 1.28.11 and earlier allows remote attackers to execute arbitrary code through proxy configuration updates. The get_secret() method passes attacker-controlled environment-variable values to Python eval() without sanitization when Google KMS is used. Exploitation requires a proxy deployment using Google KMS and access to /config/update; successful input runs code in the proxy process.

The record

CVE
CVE-2024-4264
Published
May 18, 2024
Updated
Sep 3, 2024
Vendor
Berri AI
Product
LiteLLM
Classifications
CWE-94, T1059.006
Attack vector
network
Privileges
Unavailable

Timeline

How it unfolded

  1. May 18, 2024CVE publishedPublication date reported by the CVE source.
  2. Sep 3, 2024Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0 <*
  2. Affected versionversion=unspecified <=latest

What conditions does exploitation require?

Attack vectornetwork
Required privilegesUnavailable in this record.

What is affected?

Berri AI · LiteLLMversion=0 <*; version=unspecified <=latest

Published CVSS scores

7.2GitHub Advisory DatabaseCVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H
9.8Huntr CNACVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 9, 2026Sep 15, 2026
Latest reporting daySep 15, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
PrivilegesUnavailable
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-94Improper Control of Generation of Code ('Code Injection')
T1059.006Python

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo