CVE records

Every CVE as the CVE Program publishes it, refreshed every ten minutes, with NVD's analysis, CISA's known-exploited status and a healthcare tag. Subscribers get the CVEs that match their own systems on My program, by email as they are published. Where the data comes from: sources.

Updated under an hour ago ()

What this means for you

This week: 5,437 CVEs published, 355 critical, and 7 newly confirmed exploited. Add your stack to see whether any of them hit you.

Published in the last 7 days
5,437
Show in the list
Critical, last 7 days
355
Show in the list
Healthcare-tagged, last 7 days
4
Show in the list
Known exploited (CISA KEV)
1,747
Show in the list

Showing CVEs that name the product litellm:litellm. Show all products

26 CVEs, showing 1 to 26
CVESeverityTitlePublished
CVE-2026-33634
Known exploited
Critical 9.4Trivy ecosystem supply chain briefly compromised
Assigned by GitHub_M
Mar 23, 2026
CVE-2026-35029High 8.8LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.Apr 6, 2026
CVE-2026-35030Critical 9.1LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.Apr 6, 2026
CVE-2026-40217High 8.8LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.Apr 10, 2026
CVE-2026-42271
Known exploited
High 8.7LiteLLM: Authenticated command execution via MCP stdio test endpoints
Assigned by GitHub_M
May 8, 2026
CVE-2026-42208
Known exploited
Critical 9.3LiteLLM: SQL injection in Proxy API key verification
Assigned by GitHub_M
May 8, 2026
CVE-2026-42203High 8.8LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.May 8, 2026
CVE-2026-47101High 8.8LiteLLM < 1.83.14 Privilege Escalation via API Key Generation
Assigned by VulnCheck
May 21, 2026
CVE-2026-47102High 8.8LiteLLM < 1.83.10 Privilege Escalation via User Update
Assigned by VulnCheck
May 21, 2026
CVE-2026-12770High 8.8A vulnerability was determined in BerriAI litellm up to 1.63.1.Jun 21, 2026
CVE-2026-12771High 7.5A vulnerability was identified in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-12772Medium 6.3A security flaw has been discovered in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-12773Critical 9.8A weakness has been identified in BerriAI litellm up to 1.59.8.Jun 21, 2026
CVE-2026-12774Medium 6.3A security vulnerability has been detected in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-12795High 7.3A vulnerability was determined in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-12796Medium 6.3A vulnerability was identified in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-12797Medium 6.3A security flaw has been discovered in BerriAI litellm up to 1.82.5.Jun 21, 2026
CVE-2026-12798Medium 6.3A weakness has been identified in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-12799Medium 4.3A security vulnerability has been detected in BerriAI litellm up to 1.82.2.Jun 21, 2026
CVE-2026-49468Critical 9.8LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.Jun 22, 2026
CVE-2026-59822
Known exploited
High 8.8LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback
Assigned by GitHub_M
Jul 8, 2026
CVE-2026-59819Medium 4.9LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.Jul 8, 2026
CVE-2026-59820Medium 6.5LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.Jul 8, 2026
CVE-2026-59821High 7.2LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.Jul 8, 2026
CVE-2026-108574Medium 4.3BerriAI LiteLLM Spend Tracking spend_management_endpoints.py ui_view_session_spend_logs authorization
Assigned by VulDB
Oct 11, 2026
CVE-2026-108575Medium 6.3BerriAI LiteLLM Secret Resolution main.py get_secret improper authorization
Assigned by VulDB
Oct 11, 2026

CVSS is the assigning CNA's score where it gives one, otherwise NVD's. The healthcare tag is a documented heuristic (a list of clinical and health IT vendors, and clinical terms in the description), not a classification. The CVE record is authoritative.

Your cookie choices
We use essential cookies to run this site, and, only with your consent, an advertising cookie from Google to measure whether our ads lead to sign-ups and subscriptions. See our for details.