| Component | LiteLLM |
| Severity | high (CVSS 8.8) |
| CVSS vector | CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| Published (NVD) | 2025-03-20 |
| Last modified | 2026-06-17 |
| Affected versions | < 1.65.4 = 1.65.4-dev2 |
| Fixed in | 1.65.4 |
| Weakness | CWE-94 |
| CISA KEV | not listed |
NVD description
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.
What to do
- Upgrade LiteLLM to
1.65.4or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2024-6825
- https://huntr.com/bounties/1d98bebb-6cf4-46c9-87c3-d3b1972973b5
- https://github.com/berriai/litellm/commit/441c7275ed2715f47650a7c2e525055c804073a9