Vulnerability Intelligence Report
Remote Code Execution in BerriAI/litellm
CVE-2024-6825
BerriAI/litellm version 1.40.12 contains a vulnerability that allows remote code execution. The issue exists in the handling of the 'post_call_rules' configuration, where a callback function can be added. The provided value is split at the final '.' mark, with the last part considered the function name and the remaining part appended with the '.py' extension and imported. This allows an attacker to set a system method, such as 'os.system', as a callback, enabling the execution of arbitrary commands when a chat response is processed.
No Active Exploit Signals
CVSS Base Score
8.8
HIGH
Exploitability:2.9
Impact Score:5.9
EPSS Probability:1.46%
Executive Threat Verdict
Evaluating...
Evaluating Threat Landscape...
Assessing known weaponization, exploitation telemetry, and federal advisories.
Attack Surface
—
Authentication
—
Weaponization
—
SSVC Action
—
Weaknesses (CWE)
CWE-94 ↗CWE-94 Improper Control of Generation of Code
Affected Products & Versions
| Vendor | Product | Affected Versions |
|---|---|---|
| berriai | berriai/litellm | unspecified < v1.65.4.dev6 (affected) |
References & Technical Advisories
No reference links found.
Threat Intelligence Signals
EPSS Score
1.463%
GitHub Advisory
Identity & Timeline
| Status | PUBLISHED |
| Assigning Authority | Protect AI (formerly huntr.dev) · Bug Bounty Provider · USA |
| Reserved | 2024-07-16T23:27:36 |
| Published | 2025-03-20T10:11:36 |
| Last Updated | 2025-10-15T12:49:46 |
Community Chatter & Buzz