TI-2026-42636 CVE-2026-59819 · GHSA-4g5m-c9r5-49xf
LiteLLM: Local file read via request-supplied OIDC file references
Priority LOW 12
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
Vulnerabilities
37 records
TI-2026-42639 CVE-2026-59822 · GHSA-7488-6r32-c95q
LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback
Priority CRITICAL 95KEV
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-42637 CVE-2026-59820 · GHSA-5jmr-gcrj-2c9q
LiteLLM: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Priority LOW 30
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-42638 CVE-2026-59821 · GHSA-72m8-9m7m-h278
LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
Priority LOW 13
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-36623 CVE-2026-49468 · GHSA-4xpc-pv4p-pm3w
LiteLLM: Authentication Bypass via Host Header Injection
Priority MEDIUM 54
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-10937 CVE-2026-12799 · GHSA-m2v5-74w2-qhcj
BerriAI litellm Incomplete Fix CVE-2025-0628 internal_user_endpoints.py ui_view_users improper authorization
Priority MEDIUM 57
A security vulnerability has been detected in BerriAI litellm up to 1.82.2.
TI-2026-10936 CVE-2026-12798 · GHSA-c693-x898-5g4h
BerriAI litellm MCP OpenAPI Spec Loader openapi_to_mcp_generator.py load_openapi_spec_async server-side request forgery
Priority MEDIUM 57
A weakness has been identified in BerriAI litellm up to 1.82.2.
TI-2026-10935 CVE-2026-12797 · GHSA-p897-vf7j-f5h8
BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization
Priority MEDIUM 57
A security flaw has been discovered in BerriAI litellm up to 1.82.5.
TI-2026-10934 CVE-2026-12796 · GHSA-w2mh-qq9q-453x
BerriAI litellm SSO Authentication Flow ui_sso.py get_redirect_response_from_openid session expiration
Priority MEDIUM 57
A vulnerability was identified in BerriAI litellm up to 1.82.2.
TI-2026-10933 CVE-2026-12795 · GHSA-j37q-q7p9-vpwm
BerriAI litellm SSO Debug Flow ui_sso.py json.dumps missing authentication
Priority HIGH 70
A vulnerability was determined in BerriAI litellm up to 1.82.2.
TI-2026-10919 CVE-2026-12774 · GHSA-h9c7-cfj6-h8j6
BerriAI litellm MCP Server Connection Testing rest_endpoints.py _execute_with_mcp_client server-side request forgery
Priority MEDIUM 57
A security vulnerability has been detected in BerriAI litellm up to 1.82.2.
TI-2026-10918 CVE-2026-12773 · GHSA-4jcj-7x88-m979
BerriAI litellm MCP Proxy user_api_key_auth_mcp.py UserAPIKeyAuth improper authentication
Priority HIGH 70
A weakness has been identified in BerriAI litellm up to 1.59.8.
TI-2026-10917 CVE-2026-12772 · GHSA-mf52-j94g-746m
BerriAI litellm PROXY_ADMIN database API Key Generator login_utils.py authenticate_user session expiration
Priority MEDIUM 57
A security flaw has been discovered in BerriAI litellm up to 1.82.2.
TI-2026-10916 CVE-2026-12771 · GHSA-qmf3-4767-5fg3
BerriAI litellm M2M JWT user_api_key_auth.py improper authorization
Priority MEDIUM 45
A vulnerability was identified in BerriAI litellm up to 1.82.2.
TI-2026-10915 CVE-2026-12770 · GHSA-6qr3-3g89-m4jj
BerriAI litellm Admin Key key_management_endpoints.py improper authorization
Priority MEDIUM 57
A vulnerability was determined in BerriAI litellm up to 1.63.1.
TI-2026-34701 CVE-2026-47102 · GHSA-wpfp-gwwc-vwq6
LiteLLM < 1.83.10 Privilege Escalation via User Update
Priority HIGH 73
LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint.
TI-2026-34700 CVE-2026-47101 · GHSA-qrc4-49gv-mv9m
LiteLLM < 1.83.14 Privilege Escalation via API Key Generation
Priority HIGH 73
LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit.
TI-2026-30529 CVE-2026-42208 · GHSA-r75f-5x8p-qvmc
LiteLLM: SQL injection in Proxy API key verification
Priority CRITICAL 99KEV
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-30524 CVE-2026-42203 · GHSA-xqmj-j6mv-4862
LiteLLM: Server-Side Template Injection in /prompts/test endpoint
Priority LOW 39
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-30582 CVE-2026-42271 · GHSA-v4p8-mg3p-g94g
LiteLLM: Authenticated command execution via MCP stdio test endpoints
Priority CRITICAL 97KEV
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-29027 CVE-2026-40217 · GHSA-wxxx-gvqv-xp7p
LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode…
Priority HIGH 73
LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.
TI-2026-27233 CVE-2026-35030 · GHSA-jjhc-v7c2-5hh6
LiteLLM has an authentication bypass via OIDC userinfo cache key collision
Priority MEDIUM 49
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-27232 CVE-2026-35029 · GHSA-53mr-6c8q-9789
LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint
Priority HIGH 67
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format.
TI-2026-26015 CVE-2026-33634 · GHSA-69fq-xp46-6x23
Trivy ecosystem supply chain briefly compromised
Priority CRITICAL 100KEV
Trivy is a security scanner.
TI-2025-28856 CVE-2025-45809 · GHSA-cgmh-xxmq-hp46
SQL Injection vulnerability in BerriAI LiteLLM before 1.81.0 allows attackers to execute…
Priority MEDIUM 58
SQL Injection vulnerability in BerriAI LiteLLM before 1.81.0 allows attackers to execute arbitrary commands via the key parameter to the "/key/block" and "/key/unblock" API endpoints.