LibreChat cross-site scripting in MCP server descriptions
- Exploited
- No known exploitation
- Fix
- Fixed in 0.8.6
- Who is exposed
- Not reported
Summary
Affected software is LibreChat, an AI chat application. A malicious remote MCP server can run script in a user's browser, remotely and without logging in, once that user opens the MCP configuration dialog, and the script runs in the LibreChat browser origin where it can read browser-context data or alter what is shown. A second spot, the admin banner display, can also run script for all users because it does not sanitize administrator-supplied HTML.
Written by a model
Original description
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, client/src/components/Chat/Input/MCPConfigDialog.tsx renders the remote MCP details.description value through dangerouslySetInnerHTML without sanitization, allowing a malicious MCP server to execute script when a user opens the configuration dialog. The secondary client/src/components/Banners/Banner.tsx sink similarly renders administrator-controlled banner.message HTML without sanitization for all users. Script execution occurs in the LibreChat browser origin and can expose browser-context data or alter displayed content. This issue is fixed in version 0.8.6.
What to do
Upgrade to a fixed version: 0.8.6.
Check your systems with an agent
Paste this into a coding or ops agent. It checks your systems read-only and reports a table per asset.
Check whether my systems are affected by CVE-2026-54032 (LibreChat: Remote MCP Server Description XSS via Unsanitized dangerouslySetInnerHTML; secondary Admin Banner sink lacks DOMPurify), using the cve.now data below.
Rules: work read-only. Do not run exploit code, proof-of-concept scripts or scanners that send attack payloads, and do not change any configuration, package, image or deployment. Report findings only.
What cve.now has for CVE-2026-54032 (entry last updated 2026-11-20):
Affected:
- danny-avila LibreChat: fixed in 0.8.6
Fixed versions: 0.8.6.
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
CISA KEV: CVE-2026-54032 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-54032 only. If you also check another CVE, look up its own KEV status; never assume it from this one.
How to check:
- Installed software: check what is actually running, not what a repo declares. Read the version from each host, container image and Kubernetes node (the binary's version output, the OS package database, image layers), and check whether the conditions above hold there. Distribution packages may carry a backported fix under an older version number; confirm against the distribution's own advisory.
Verify against the linked advisories before concluding, and cite the date you read each one:
- https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-vfg3-f8h3-2683
- https://github.com/LibreChat-AI/LibreChat/pull/12927
- https://github.com/LibreChat-AI/LibreChat/commit/619f28d76d73ff34448451ed25a9629e6c28a640
- https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.6
Do not conclude an asset is unaffected unless you checked it and the evidence covers both its version and the conditions above. If you could not check something, mark it unknown and say what is missing.
Report a table with one row per asset and these columns: Asset | Version or build | Status (affected, fixed, not applicable, unknown) | Compensating controls | Exposure (internet-facing, internal, none) | Evidence | Next action.
Entry: https://cve.now/CVE-2026-54032
For follow-up questions, use the cve.now MCP server at https://mcp.cve.now/mcp (no authentication), for example execute with name cve.get and arguments {"id": "CVE-2026-54032"}.Affected versions
- danny-avila LibreChatfixed in 0.8.6
cve.now Index
- Exploitation?/40Unknown. No CISA SSVC exploitation rating yet
- Exposure7/25Reachable over the network without a login · Unknown: No advisory context yet
- Reach?/20Unknown. No tracked technology or package matched
- Severity6.1/10CVSS 6.1
- No patch0/5No signal
What would change the score
- Would score about 68 if added to CISA KEV
- Would score about 63 if CISA's SSVC rates exploitation active
- Would score about 28 if advisories confirm default setups are exposed
Timeline
- CVE published
- First seen by cve.now
Evidence 6
| Kind | Source |
|---|---|
| Vendor advisory 1Establishes: Affected and fixed versions. | |
| Advisory | GitHub · LibreChat-AI/LibreChat · Advisory GHSA-vfg3-f8h3-2683 |
| CVE record 2Establishes: The identifier and description. | |
| Record | CVE List · CVE-2026-54032 |
| Record | NVD · CVE-2026-54032 |
| Other links 3 | |
| Repository | GitHub · LibreChat-AI/LibreChat · Pull request #12927 |
| Repository | GitHub · LibreChat-AI/LibreChat · Commit 619f28d7 |
| Repository | GitHub · LibreChat-AI/LibreChat · Release v0.8.6 |
Questions about CVE-2026-54032
Is CVE-2026-54032 being exploited?
It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.
Source: cve.now feed data
Which versions are affected by CVE-2026-54032?
LibreChat: before 0.8.6.
Source: cve.now feed data
How do I fix CVE-2026-54032?
Upgrade to a fixed version: 0.8.6.
Source: cve.now feed data
Related
- CVE-2026-32625LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
- CVE-2026-54039LibreChat: Pre-registration account takeover via attacker-controlled `provider` field and social-login email fallback
- CVE-2026-54030LibreChat: Missing Resource Parameter Validation in MCP OAuth Flow
- CVE-2026-54033LibreChat: SSRF via User-Provided Custom Endpoint baseURL — no private IP validation on user-configured API base URLs
- CVE-2026-31942LibreChat has IDOR in API Keys Management that allows any authenticated user to overwrite other users' API keys
- CVE-2026-54042LibreChat: Missing Rate Limiting on 2FA Verification Endpoint Allows TOTP Guessing Attempts
No corrections so far. Something wrong on this page? Report an error.