| Component | LiteLLM |
| Severity | critical (CVSS 9.8) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| Published (NVD) | 2024-06-27 |
| Last modified | 2026-06-17 |
| Affected versions | < 1.40.16 from the GitHub-reviewed advisory GHSA-gppg-gqw8-wh9g |
| Fixed in | 1.40.16 |
| Weakness | CWE-94 |
| CISA KEV | not listed |
NVD description
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.
What to do
- Upgrade LiteLLM to
1.40.16or later. - Do not expose the component's API or UI to the internet without authentication in front of it.