How severe is CVE-2025-0330?

CVE-2025-0330 has a CVSS 3.x base score of 7.5, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability none.

Is CVE-2025-0330 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (41st percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2025-0330?

CVE-2025-0330 affects Litellm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2025-0330?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.

Does CVE-2025-0330 have an EU (EUVD) identifier?

Yes. CVE-2025-0330 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-6833.

When was CVE-2025-0330 published?

CVE-2025-0330 was published on 2025-03-20 and last updated on 2026-06-17.

CVE-2025-0330

CVE-2025-0330 is a high-severity vulnerability in Litellm with a CVSS 3.x base score of 7.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-1230.

Key facts

Severity: High (CVSS 3.x base score 7.5)
EPSS exploit prediction: 1% (41st percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2025-6833
Weakness: CWE-1230
Affected product: Litellm
Published: 2025-03-20
Last modified: 2026-06-17

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.

Frequently asked questions

What is CVE-2025-0330?: 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.
How severe is CVE-2025-0330?: CVE-2025-0330 has a CVSS 3.x base score of 7.5, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability none.
Is CVE-2025-0330 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (41st percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2025-0330?: CVE-2025-0330 affects Litellm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2025-0330?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
Does CVE-2025-0330 have an EU (EUVD) identifier?: Yes. CVE-2025-0330 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-6833.
When was CVE-2025-0330 published?: CVE-2025-0330 was published on 2025-03-20 and last updated on 2026-06-17.

References

https://huntr.com/bounties/661b388a-44d8-4ad5-862b-4dc5b80be30a

Affected products (1)

cpe:2.3:a:litellm:litellm:1.52.1:-:*:*:*:*:*:*

More vulnerabilities in Litellm

CVE-2026-49468 — Critical (CVSS 9.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, This…
CVE-2026-42208 — Critical (CVSS 9.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before…
CVE-2024-5751 — Critical (CVSS 9.8): BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The…
CVE-2024-2952 — Critical (CVSS 9.8): BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The…
CVE-2026-35030 — Critical (CVSS 9.1): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, when JWT…
CVE-2026-47102 — High (CVSS 8.8): LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint. While the endpoint…

All CVEs affecting Litellm →

Other CWE-1230 vulnerabilities

CVE-2024-9099 — High (CVSS 8.1): In lunary-ai/lunary version v1.4.29, the GET /projects API endpoint exposes both public and private API keys for all…
CVE-2025-13084 — High (CVSS 7.6): The users endpoint in the groov View API returns a list of all users and associated metadata including their API keys.…
CVE-2025-47324 — High (CVSS 7.5): Information disclosure while accessing and modifying the PIB file of a remote device via powerline.
CVE-2024-53291 — High (CVSS 7.5): Dell NativeEdge, version(s) 2.1.0.0, contain(s) an Exposure of Sensitive Information Through Metadata vulnerability. An…
CVE-2025-30038 — High (CVSS 7.3): The vulnerability consists of a session ID leak when saving a file downloaded from CGM CLININET. The identifier is…
CVE-2024-47517 — Medium (CVSS 6.8): Expired and unusable administrator authentication tokens can be revealed by units that have timed out from ETM access

Browse all CWE-1230 vulnerabilities →