litellm-command-injection-security-assessment

CVE-2026-42271 - LiteLLM AI 网关 MCP 命令注入 RCE 顾问式网络安全报告 专业漏洞评估报告，针对 LiteLLM 命令注入风险，包括高管摘要、技术影响、修复及缓解策略。 📍 报告快照 字段| 详情 ---|--- 报告类型| 漏洞评估报告 参与背景| 安全研究 主要关注点| 应用安全 受众| 安全团队、工程团队、招聘经理 输出风格| 高管摘要、技术分析、业务影响、修复路线图 发布状态| 已脱敏，供公开作品集审阅 !IMPORTANT 本报告已特意脱敏，以在 GitHub 上公开发布。敏感标识符、凭证、基础设施值及客户特定证据均替换为明确的占位符。 🧭...

CVE-2026-84377 LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials t...

aegis-latent-core

🛡️ Aegis Latent Core AI Governance and Cryptographic Evidence Gateway Provider-independent request controls, bounded streaming PII redaction, and client-verifiable Merkle Mountain Range inclusion proofs for governed LLM traffic. Last verified: 2026-08-27 UTC Release baseline: che...

CVE-2026-42208

✦ CVE-2026-42208 - LiteLLM 中的严重 SQL 注入漏洞 🧭 概述 CVE-2026-42208 是一个影响 LiteLLM AI 网关的严重的预认证 SQL 注入漏洞 。 它允许攻击者在无需认证 的情况下利用后端数据库查询，可能暴露敏感的 AI 基础设施数据。 📦 受影响软件 LiteLLM 受影响版本：1.81.16 → 1.83.6 🧨 漏洞类型 root@kitploit: SQL 注入（预认证） 无需登录 🚫 可通过 HTTP 请求操作进行利用 直接针对后端数据库层 📊 严重等级 🔴 严重 CVSS 评分：9.3 – 9.9...

CVE-2026-82270

Portkey AI Gateway through 1.15.2 contains a server-side request forgery vulnerability in the /v1/proxy/ route that lacks requestValidator middleware. Attackers can set the x-portkey-custom-host header to internal addresses and forward requests with Authorization headers to reach internal service...

CVE-2026-55245

Bifrost is an enterprise AI gateway for routing requests to model providers. Prior to 1.5.17, the isPublicIP function in core/providers/utils/fetch.go, reached through FetchAndEncodeURL for Bedrock and Vertex image or document URLs, classifies Carrier-Grade NAT 100.64.0.0/10, IPv6 6to4 2002::/16,...

CVE-2026-55245

Bifrost is an enterprise AI gateway for routing requests to model providers. Prior to 1.5.17 , the isPublicIP function in core/providers/utils/fetch.go (reached via FetchAndEncodeURL for Bedrock and Vertex image/document URLs) incorrectly classifies CGNAT (100.64.0.0/10) , IPv6 6to4 (2002::/16) ,...

CVE-2026-82270 Portkey AI Gateway Server-Side Request Forgery via /v1/proxy/*

Portkey AI Gateway through 1.15.2 contains a server-side request forgery vulnerability in the /v1/proxy/ route that lacks requestValidator middleware. Attackers can set the x-portkey-custom-host header to internal addresses and forward requests with Authorization headers to reach internal service...

EUVD-2026-67801

Portkey AI Gateway through 1.15.2 contains a server-side request forgery vulnerability in the /v1/proxy/ route that lacks requestValidator middleware. Attackers can set the x-portkey-custom-host header to internal addresses and forward requests with Authorization headers to reach internal service...

CVE-2026-82270 Portkey AI Gateway Server-Side Request Forgery via /v1/proxy/*

Portkey AI Gateway through 1.15.2 contains a server-side request forgery vulnerability in the /v1/proxy/ route that lacks requestValidator middleware. Attackers can set the x-portkey-custom-host header to internal addresses and forward requests with Authorization headers to reach internal service...

CVE-2026-82270

Portkey AI Gateway through version 1.15.2 contains a Server-Side Request Forgery (SSRF) vulnerability in the /v1/proxy/* route. The root cause is the absence of the requestValidator middleware on that endpoint. An unauthenticated attacker can set the x-portkey-custom-host header to an internal ad...

CVE-2026-75871

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.10 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect outbound model requests to an...

CVE-2026-19889

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.9.0 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect model requests to an...

EUVD-2026-67088

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.10 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect outbound model requests to an...

CVE-2026-75871 Server-Side Request Forgery (SSRF) in GitLab AI Gateway

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.10 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect outbound model requests to an...

CVE-2026-75871

GitLab AI Gateway (versions 18.10–19.0.12, 19.1–19.1.7, and 19.2–19.2.2) is affected by a Server-Side Request Forgery (SSRF) vulnerability. An authenticated user with Duo Agent Platform access could craft an inline flow configuration that overrides the HTTP Host header, redirecting outbound model...

EUVD-2026-67087

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.9.0 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect model requests to an...

CVE-2026-19889 Server-Side Request Forgery (SSRF) in GitLab AI Gateway

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.9.0 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect model requests to an...

CVE-2026-19889

CVE-2026-19889 is a Server-Side Request Forgery (SSRF) vulnerability in the GitLab AI Gateway component, affecting versions 18.9.0 through 19.0.12 , 19.1 through 19.1.7 , and 19.2 through 19.2.2 . An authenticated user with Duo Agent Platform access could redirect model requests to an externally-...

CVE-2026-71211

A flaw was found in MLflow's AI Gateway where an unvalidated apibase value in a gateway secret could lead to a Server-Side Request Forgery SSRF vulnerability. An authenticated user, even with read-only privileges, can create a secret with an internal network address. This allows the gateway proxy...