CVE-2024-5751 | Remote Code Execution in BerriAI/litellm

BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the `add_deployment` function, which decodes and decrypts environment variables from base64 and assigns them to `os.environ`. An attacker can exploit this by sending a malicious payload to the `/config/update` endpoint, which is then processed and executed by the server when the `get_secret` function is triggered. This requires the server to use Google KMS and a database to store a model.

Published: 2024-06-27 Last update: 2024-11-21 Assigner: [email protected] Source: [email protected]
NVD Status：Modified，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2024-5751 is rated High Risk (73.8/100): CVSS Critical severity, with medium exploitation likelihood (EPSS 5.36%). EPSS rose +3.22% over the last day, indicating growing attacker interest. High exploitation likelihood—assess exposure and prioritize remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2024-5751

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2025-11-21 2.14% 5.36% +3.22%
2 2025-11-18 5.36% 2.14% -3.22%
3 2025-11-16 — 5.36% —

Full EPSS history (11 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2024-5751

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]
9.8 3.0 CRITICAL
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]

Weakness enumeration for CVE-2024-5751

GitHub Security Advisory for CVE-2024-5751

GHSA-gppg-gqw8-wh9g · Severity: critical · Ecosystem: pip — litellm vulnerable to remote code execution based on using eval unsafely

Affected software / configurations for CVE-2024-5751

Vendor Product Version Raw CPE
litellm litellm 1.35.8 cpe:2.3:a:litellm:litellm:1.35.8:*:*:*:*:*:*:*

References for CVE-2024-5751

cvelogic Threat Intelligence