Missing redirect target validation in MCP OAuth fetch in LibreChat
LibreChat-AI LibreChat
At a glance
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.8, packages/api/src/mcp/oauth/handler.ts createOAuthFetch validates only the initial destination for MCP OAuth discovery, registration, token, refresh, and revocation requests, then uses redirect-following fetch behavior without validating each redirect target. An attacker who can initiate MCP OAuth against a controlled endpoint can redirect server requests to internal or private addresses, reaching services that the initial SSRF checks should block. The separate MCP transport path already validates redirects and is not affected. This issue is fixed in version 0.8.8.
Source description · CVE List / CNA
System impact
CVSS summary v3.1
- Published:
- Updated:
- EPSS:
- Not specified
- Exploited in attacks:
- Not confirmed
- Ransomware campaigns:
- Not confirmed
- Attack vector:
- Network
Related CWE
Affected software
Vendor, product and affected version ranges.
| Vendor | Product | Affected versions |
|---|---|---|
| Vendor:LibreChat-AI | LibreChat | Affected versions: < 0.8.8 |
| Vendor:danny-avila | LibreChat | Affected versions: < 0.8.8 |
1–2 of 2 · Page 1 of 1
CVSS scores and metrics4
GitHub_M · CVE List / CNA (cna)Primary6.3 / 10MediumCVSS 3.1Details
- Attack complexity
- High
- Confidentiality
- High
- Integrity
- None
- Availability
- None
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- Not required
- Scope
- Changed
Source vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N[email protected] · NVD (Secondary)6.3 / 10MediumCVSS 3.1Details
- Attack complexity
- High
- Confidentiality
- High
- Integrity
- None
- Availability
- None
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- Not required
- Scope
- Changed
Source vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:NCVE-2026-54031 · OSV (source-vector)6.3 / 10MediumCVSS 3.1Details
- Attack complexity
- High
- Confidentiality
- High
- Integrity
- None
- Availability
- None
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- Not required
- Scope
- Changed
Source vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:NENISA · ENISA EUVD (aggregator)6.3 / 10MediumCVSS 3.1Details
- Attack complexity
- High
- Confidentiality
- High
- Integrity
- None
- Availability
- None
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- Not required
- Scope
- Changed
Source vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:NCVSS measures severity; EPSS estimates exploitation probability. Lack of confirmed attacks does not mean lack of risk.
This product uses the NVD API but is not endorsed or certified by the NVD. CVE® records © The MITRE Corporation, reproduced under the CVE Terms of Use. Data sources and licences