彙總 litellm 相關全部產品的 CVE 與安全漏洞情報，包括 CVSS、EPSS、公開時間與漏洞情報資料。
常見弱點模式包括 SQL 注入、路徑處理缺陷、SSRF與跨站腳本，在 軟體部署與生產負載 使用場景中可能帶來 檔案覆寫、資料外洩與工作階段劫持 等風險。
相關漏洞資料主要來源於公開漏洞披露與安全公告，可用於評估歷史漏洞暴露面與修補優先順序。
| CVE | 摘要 | 來源 | 最高 CVSS | EPSS % | 公開時間 | 更新時間 |
|---|---|---|---|---|---|---|
| CVE-2026-49468 | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, This vulnerability is fixed in 1.84.0. | [email protected] | 9.5 | 0.56% | 2026-06-22 | 2026-06-29 |
| CVE-2026-12799 | A security vulnerability has been detected in BerriAI litellm up to 1.82.2. Affected by this issue is the function ui_view_users of the file litellm/proxy/management_endpoints/internal_user_endpoints.py of the component Incomplete Fix CVE-2025-0628. Such manipulation leads to improper authorization. It is possible to launch the attack remotely. The exploit has been disclosed publicly and may be used. The vendor was contacted early about this disclosure. | [email protected] | 2.1 | 0.29% | 2026-06-21 | 2026-06-24 |
| CVE-2026-12798 | A weakness has been identified in BerriAI litellm up to 1.82.2. Affected by this vulnerability is the function load_openapi_spec_async of the file litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py of the component MCP OpenAPI Spec Loader. This manipulation of the argument spec_path causes server-side request forgery. It is possible to initiate the attack remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early abou | [email protected] | 2.1 | 0.26% | 2026-06-21 | 2026-06-24 |
| CVE-2026-12797 | A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure. | [email protected] | 2.1 | 0.21% | 2026-06-21 | 2026-06-24 |
| CVE-2026-12796 | A vulnerability was identified in BerriAI litellm up to 1.82.2. This impacts the function get_redirect_response_from_openid of the file litellm/proxy/management_endpoints/ui_sso.py of the component SSO Authentication Flow. The manipulation leads to session expiration. The attack is possible to be carried out remotely. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure. | [email protected] | 2.1 | 0.36% | 2026-06-21 | 2026-06-24 |
| CVE-2026-12795 | A vulnerability was determined in BerriAI litellm up to 1.82.2. This affects the function json.dumps of the file litellm/proxy/management_endpoints/ui_sso.py of the component SSO Debug Flow. Executing a manipulation can lead to missing authentication. The attack can be executed remotely. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure. | [email protected] | 5.5 | 0.51% | 2026-06-21 | 2026-06-24 |
| CVE-2026-12774 | A security vulnerability has been detected in BerriAI litellm up to 1.82.2. Affected by this vulnerability is the function _execute_with_mcp_client of the file litellm/proxy/_experimental/mcp_server/rest_endpoints.py of the component MCP Server Connection Testing. The manipulation leads to server-side request forgery. Remote exploitation of the attack is possible. The exploit has been disclosed publicly and may be used. The vendor was contacted early about this disclosure. | [email protected] | 2.1 | 0.26% | 2026-06-21 | 2026-06-24 |
| CVE-2026-12773 | A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be launched remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure. | [email protected] | 5.5 | 0.60% | 2026-06-21 | 2026-06-29 |
| CVE-2026-12772 | A security flaw has been discovered in BerriAI litellm up to 1.82.2. This impacts the function authenticate_user of the file litellm/proxy/auth/login_utils.py of the component PROXY_ADMIN database API Key Generator. Performing a manipulation results in session expiration. The attack may be initiated remotely. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure. | [email protected] | 2.1 | 0.26% | 2026-06-20 | 2026-06-24 |
| CVE-2026-12771 | A vulnerability was identified in BerriAI litellm up to 1.82.2. This affects an unknown function of the file litellm/proxy/auth/user_api_key_auth.py of the component M2M JWT Handler. Such manipulation leads to improper authorization. The attack can be launched remotely. A high complexity level is associated with this attack. The exploitability is reported as difficult. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure. | [email protected] | 1.3 | 0.29% | 2026-06-20 | 2026-06-24 |
| CVE-2026-12770 | A vulnerability was determined in BerriAI litellm up to 1.63.1. The impacted element is an unknown function of the file litellm/proxy/management_endpoints/key_management_endpoints.py of the component Admin Key Handler. This manipulation causes improper authorization. The attack can be initiated remotely. The exploit has been publicly disclosed and may be utilized. Patch name: 23781. It is recommended to apply a patch to fix this issue. The vendor was contacted early about this disclosure. | [email protected] | 2.1 | 0.34% | 2026-06-20 | 2026-06-24 |
| CVE-2026-47102 | LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint. While the endpoint correctly restricts users to updating only their own account, it does not restrict which fields may be changed. A user who can reach this endpoint can set their role to proxy_admin, gaining full administrative access to LiteLLM including all users, teams, keys, models, and prompt history. Users with the org_admin role have legitimate access to this endpoint and can exploit this | [email protected] | 8.7 | 0.65% | 2026-05-21 | 2026-07-02 |
| CVE-2026-47101 | 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. When generating a key, the allowed_routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with access to admin-only routes can then be used to reach those routes successfully, bypassing the role-based access controls that would otherwise block the request, enabling full privilege escalation from | [email protected] | 8.7 | 0.74% | 2026-05-21 | 2026-07-01 |
| CVE-2026-42271 KEV | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied com | [email protected] | 8.7 | 80.19% | 2026-05-08 | 2026-06-30 |
| CVE-2026-42208 KEV | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker co | [email protected] | 9.3 | 86.61% | 2026-05-08 | 2026-06-29 |
| CVE-2026-42203 | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets | [email protected] | 8.6 | 0.37% | 2026-05-08 | 2026-06-29 |
| CVE-2026-40217 | LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI. | [email protected] | 8.8 | 6.50% | 2026-04-10 | 2026-06-29 |
| CVE-2026-35030 | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, when JWT authentication is enabled (enable_jwt_auth: true), the OIDC userinfo cache uses token[:20] as the cache key. JWT headers produced by the same signing algorithm generate identical first 20 characters. This configuration option is not enabled by default. Most instances are not affected. An unauthenticated attacker can craft a token whose first 20 characters match a legitimate user's cach | [email protected] | 9.4 | 0.49% | 2026-04-06 | 2026-06-29 |
| CVE-2026-35029 | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment variables, register custom pass-through endpoint handlers pointing to attacker-controlled Python code, achieving remote code execution, read arbitrary server files by setting UI_LOGO_PATH and fetchin | [email protected] | 8.7 | 26.41% | 2026-04-06 | 2026-06-29 |
| CVE-2026-33634 KEV | Trivy is a security scanner. On March 19, 2026, a threat actor used compromised credentials to publish a malicious Trivy v0.69.4 release, force-push 76 of 77 version tags in `aquasecurity/trivy-action` to credential-stealing malware, and replace all 7 tags in `aquasecurity/setup-trivy` with malicious commits. This incident is a continuation of the supply chain attack that began in late February 2026. Following the initial disclosure on March 1, credential rotation was performed but was not atomi | [email protected] | 9.4 | 60.37% | 2026-03-23 | 2026-06-17 |