Access-token theft via unvalidated OAuth resource
Published Jun 25, 2026 · Updated Jun 25, 2026
OAuth resource validation failure in LibreChat before 0.8.5 allows remote attackers to steal MCP access tokens through malicious metadata. In packages/api/src/mcp/oauth/handler.ts, the OAuth handler copies the metadata resource URL into the authorization request without matching it to the configured MCP server. Exploitation requires a victim to configure an attacker-controlled OAuth-protected MCP server and complete its legitimate-looking authorization flow, after which the server receives a token usable to impersonate the victim at the legitimate MCP service.
Summary
What happened
OAuth resource validation failure in LibreChat before 0.8.5 allows remote attackers to steal MCP access tokens through malicious metadata. In packages/api/src/mcp/oauth/handler.ts, the OAuth handler copies the metadata resource URL into the authorization request without matching it to the configured MCP server. Exploitation requires a victim to configure an attacker-controlled OAuth-protected MCP server and complete its legitimate-looking authorization flow, after which the server receives a token usable to impersonate the victim at the legitimate MCP service.
The record
- CVE
- CVE-2026-54030
- Published
- Jun 25, 2026
- Updated
- Jun 25, 2026
- Vendor
- Danny Avila
- Product
- LibreChat
- Classifications
- CWE-346, T1528
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 25, 2026CVE publishedPublication date reported by the CVE source.
- Jun 25, 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=< 0.8.5
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.
Public exploit references
- GitHub advisory OAuth metadata 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