| Component | LiteLLM |
| Severity | high (CVSS 7.7) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N |
| Published (NVD) | 2026-04-03 |
| Last modified | 2026-07-24 |
| Affected versions | praisonai < 4.5.90 |
| Fixed in | 4.5.90 |
| Weakness | CWE-918 |
| CISA KEV | not listed |
NVD description
PraisonAI is a multi-agent teams system. Prior to version 4.5.90, passthrough() and apassthrough() in praisonai accept a caller-controlled api_base parameter that is concatenated with endpoint and passed directly to httpx.Client.request() when the litellm primary path raises AttributeError. No URL scheme validation, private IP filtering, or domain allowlist is applied, allowing requests to any host reachable from the server. This issue has been patched in version 4.5.90.
What to do
- Upgrade LiteLLM to
4.5.90or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-34936
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-x6m9-gxvr-7jpv
Read more
Other LiteLLM CVEs
A flaw has been found in BerriAI LiteLLM up to 1.95.0. Affected by this issue is the function ui_view_session_spend_logs of the file litellm...
A vulnerability has been found in BerriAI LiteLLM up to 1.94.0. This affects the function get_secret of the file secret_managers/main.py of...
LiteLLM contains a weak authentication vulnerability that allows an attacker holding a valid JWT from the configured identity provider to au...
BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated u...
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller...
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated...