6 matches found
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-2026-85025 Langflow is vulnerable to arbitrary code execution due to multiple incomplete code security controls and missing execution guards
IBM Langflow OSS 1.0.0 through 1.11.5 Langflow could allow an unauthenticated attacker to execute arbitrary code and access or modify chat sessions through publicly shared MCP project endpoints due to improper enforcement of public-flow security restrictions and session isolation controls...
CVE-2026-44653
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...
CVE-2026-5382 runZero Platform MCP endpoint information leak
An issue that could expose records outside of the authorized organization scope through the MCP endpoints has been resolved. This is an instance of CWE-863: Incorrect Authorization, and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:L/I:N/A:N 3.0 Low. This issue was fixed in...
CVE-2026-5382
The CVE-2026-5382 entry concerns the runZero Platform, specifically the MCP endpoint information leak. The underlying issue is CWE-863 (Incorrect Authorization), allowing records to be exposed outside the authorized organization scope via MCP endpoints. The CVSS v3.1 impact is low (3.0) with vect...
