MediumVulnerabilityLLM-specific
CVE-2026-54032: LibreChat cross-site scripting in MCP configuration dialog and banner
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-54032
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
Summary
LibreChat versions prior to 0.8.6 render the remote MCP details.description value through dangerouslySetInnerHTML without sanitization in client/src/components/Chat/Input/MCPConfigDialog.tsx. A malicious MCP server can therefore run script when a user opens the configuration dialog. A second unsanitized sink in client/src/components/Banners/Banner.tsx renders administrator-controlled banner.message HTML for all users, and script there can expose browser-context data or alter displayed content in the LibreChat origin.
Mitigation
Fixed in version 0.8.6.
Topics
Related items
- MediumCVE-2026-54026: LibreChat message injection via conversationId in request bodySimilar attack · NVD/CVE Database
- MediumCVE-2026-54046: LibreChat unauthenticated account enumeration via /api/user/verifySimilar attack · NVD/CVE Database
- HighCVE-2026-54044: LibreChat credential exposure through agent action domain repointingSimilar attack · NVD/CVE Database
- MediumCVE-2026-54043: LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7…Similar attack · NVD/CVE Database
- MediumCVE-2026-54042: LibreChat 2FA verification unlimited code guessing via temp token endpointSimilar attack · NVD/CVE Database