6 matches found
litellm-command-injection-security-assessment
CVE-2026-42271 - LiteLLM AI Gateway MCP Command Injection RCE 컨설턴트 스타일 사이버보안 보고서 LiteLLM 명령 주입 위험에 대한 전문 취약점 평가 보고서로, 경영진 요약, 기술적 영향, 수정 및 완화 전략을 포함합니다. 📍 보고서 스냅샷 항목| 세부 정보 ---|--- 보고서 유형| 취약점 평가 보고서 계약 맥락| 보안 연구 주요 초점| 애플리케이션 보안 대상 독자| 보안 팀, 엔지니어링 팀, 채용 관리자 출력 스타일| 경영진 요약, 기술 분석, 비즈니스 영향, 수정 로드맵...
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...
