litellm-sqli-scanner

LiteLLM SQL 注入扫描器 CVE-2026-42208 — LiteLLM 代理中的 SQL 注入 检测并验证 CVE-2026-42208：LiteLLM 代理数据库层中的 SQL 注入漏洞。 仅限授权安全测试使用。 功能 CVE-2026-42208 SQL 注入检测 LiteLLM 代理版本指纹识别 PoC 验证载荷 结构化 JSON / 文本输出 环境要求 Python 3.8+ 使用方法 root@kitploit: python litellmscanner.py --url http://target:4000 Scan a target python...

CVE-2026-42208-Lab

CVE-2026-42208 — LiteLLM 预认证 SQL 注入计时 PoC 本地 Docker 实验环境及针对 CVE-2026-42208 的最小危害 PoC，该漏洞是 LiteLLM Proxy API 密钥验证路径中的预认证 SQL 注入漏洞。 本仓库通过基于计时的 PostgreSQL pgsleep 证明，演示了存在漏洞的 LiteLLM 实例与已修补的 LiteLLM 实例之间的差异。 范围：仅限本地实验环境 / 授权测试。默认 PoC 不会转储数据库数据，也不会修改数据库数据。 概述 CVE-2026-42208 影响 LiteLLM Proxy 1.81.16 至...

CVE-2026-42208_lab

LiteLLM Proxy SQL 注入（GHSA-r75f-5x8p-qvmc） 一个用于复现 LiteLLM Proxy API 密钥认证流程中 SQL 注入漏洞的环境。 漏洞摘要 项目| 详情 ---|--- 安全公告| GHSA-r75f-5x8p-qvmc 类型| SQL 注入（CWE-89） 严重程度| 严重 受影响版本| litellm =1.81.16, =1.83.7（提交 4dc416ee74） 攻击路径 注入发生在错误处理回调路径 中，而非主认证流程。当发送非 sk- 前缀的令牌时，断言失败，原始（未哈希）令牌会流经失败回调链，进入使用 f-string 插值的 S...

VulnCheck KEV: CVE-2026-59821

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

EUVD-2026-42350

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks...

EUVD-2026-42359

LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback...

EUVD-2026-42361

LiteLLM: Local file read via request-supplied OIDC file references...

CVE-2026-59821

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

Weekly Metasploit Update: Modules for Audiobookshelf, LiteLLM, Next.js, Dalfox and more

Help shape the future of Metasploit Framework We are planning future work in relation to the evasion capabilities present in Metasploit Framework, and how they function/are presented to users. We are currently accepting responses to our feedback form, which means that you can shape the future of...

User Impersonation

Overview litellm-proxy-extras is an Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package. Affected versions of this package are vulnerable to User Impersonation via manipulation of the Host header during HTTP requests. An attacker can gain unauthorized access to...

GHSA-4XPC-PV4P-PM3W LiteLLM: Authentication Bypass via Host Header Injection

Impact A Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/authutils.py::getrequestroute, which Starlette reconstructs...

Remote Code Execution (RCE)

LiteLLM is vulnerable to Remote Code Execution RCE. The vulnerability is due to unsafe rendering of user-supplied prompt templates in the POST /prompts/test endpoint without sandboxing, allowing authenticated users to execute arbitrary code within the LiteLLM Proxy process and potentially access...

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...

CVE-2026-42208 LiteLLM: SQL injection in Proxy API key verification

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...

EUVD-2026-28502

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...

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...

EUVD-2026-28507

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 i...

CVE-2026-42271

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 i...

Exploit for CVE-2026-42208

LiteLLM Proxy SQL Injection GHSA-r75f-5x8p-qvmc A reproduct...

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...