Authenticated secret exfiltration via MCP URL expansion
Published Jun 2, 2026 · Updated Jun 2, 2026
Information disclosure in LibreChat 0.8.3 and earlier allows remote authenticated users to exfiltrate server secrets via MCP URLs. The MCP user-input schema in packages/data-provider/src/mcp.ts applies extractEnvVariable to untrusted SSE, HTTP, and WebSocket URLs, replacing ${VAR} tokens with process.env values before MCPServerInspector connects to the resolved endpoint. Any registered user account is sufficient, and the resulting request can expose encryption keys, JWT signing material, and database credentials to an attacker-controlled server.
Summary
What happened
Information disclosure in LibreChat 0.8.3 and earlier allows remote authenticated users to exfiltrate server secrets via MCP URLs. The MCP user-input schema in packages/data-provider/src/mcp.ts applies extractEnvVariable to untrusted SSE, HTTP, and WebSocket URLs, replacing ${VAR} tokens with process.env values before MCPServerInspector connects to the resolved endpoint. Any registered user account is sufficient, and the resulting request can expose encryption keys, JWT signing material, and database credentials to an attacker-controlled server.
The record
- CVE
- CVE-2026-32625
- Published
- Jun 2, 2026
- Updated
- Jun 2, 2026
- Vendor
- Danny Avila
- Product
- LibreChat
- Classifications
- CWE-200, T1190
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jun 2, 2026CVE publishedPublication date reported by the CVE source.
- Jun 2, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.8.4-rc1
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-4pcc-j6m6-wcwx proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo