CVE-2025-0330 Exposure of Sensitive Information in berriai/litellm
Attackers can obtain Langfuse API keys via error messages, granting full access to stored request data in LiteLLM deployments.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2025-0330?
CVE-2025-0330 is a high-severity vulnerability in berriai/litellm, published on 20 Mar 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
In berriai/litellm version v1.52.1, an issue in proxy_server.py causes the leakage of Langfuse API keys when an error occurs while parsing team settings. This vulnerability exposes sensitive information, including langfuse_secret and langfuse_public_key, which can provide full access to the Langfuse project storing all requests.
Weakness: CWE-1230
Which versions are affected by CVE-2025-0330?
3 open source packages ship an affected version, including litellm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
litellm PyPI | All versions to 1.52.1 | None |
litellm PyPI | All versions to 1.52.1 | None |
litellm PyPI | All versions to 1.52.1 | None |
Products include Litellm Litellm.
How do I fix CVE-2025-0330?
No fix has been published for CVE-2025-0330 yet. Limit exposure of the affected software until one is available.
Is CVE-2025-0330 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-0330 exists.
Other vulnerabilities in berriai/litellm
Sources
Also known as GHSA-879v-fggm-vxw2, PYSEC-2026-1543.