CVE-2026-14541: CWE-287 (Improper Authentication) in Google mcp-toolbox
CVE-2026-14541 is an authentication bypass vulnerability in Google mcp-toolbox version 1.4.0. The flaw occurs when the Google OAuth provider component is initialized with mcpEnabled set to true but without an explicitly defined audience or clientId. This causes the ValidateMCPAuth pipeline to skip audience validation for opaque tokens, allowing acceptance of any valid Google OAuth access token, even those intended for unrelated applications. This can grant unauthorized access to protected tools and data backends.
AI Analysis
Technical Summary
The vulnerability in Google mcp-toolbox 1.4.0 involves improper authentication due to missing audience or clientId configuration in the Google OAuth provider component. When mcpEnabled is true and no audience/clientId is specified, the ValidateMCPAuth pipeline does not validate the token audience, resulting in acceptance of any valid Google OAuth access token regardless of its intended audience. This leads to an authentication bypass where unauthorized clients can access protected resources.
Potential Impact
Unauthorized clients can gain access to protected tools and data backends by presenting valid Google OAuth access tokens minted for unrelated ecosystem applications. This bypasses intended audience restrictions and compromises the authentication mechanism, potentially exposing sensitive data or functionality.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, ensure that the Google OAuth provider component is configured with an explicit audience or clientId when mcpEnabled is true to enforce proper token audience validation.
CVE-2026-14541: CWE-287 (Improper Authentication) in Google mcp-toolbox
Description
CVE-2026-14541 is an authentication bypass vulnerability in Google mcp-toolbox version 1.4.0. The flaw occurs when the Google OAuth provider component is initialized with mcpEnabled set to true but without an explicitly defined audience or clientId. This causes the ValidateMCPAuth pipeline to skip audience validation for opaque tokens, allowing acceptance of any valid Google OAuth access token, even those intended for unrelated applications. This can grant unauthorized access to protected tools and data backends.
CVSS v4.0
Score 8.0high
Affected software
mcp-toolbox
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in Google mcp-toolbox 1.4.0 involves improper authentication due to missing audience or clientId configuration in the Google OAuth provider component. When mcpEnabled is true and no audience/clientId is specified, the ValidateMCPAuth pipeline does not validate the token audience, resulting in acceptance of any valid Google OAuth access token regardless of its intended audience. This leads to an authentication bypass where unauthorized clients can access protected resources.
Potential Impact
Unauthorized clients can gain access to protected tools and data backends by presenting valid Google OAuth access tokens minted for unrelated ecosystem applications. This bypasses intended audience restrictions and compromises the authentication mechanism, potentially exposing sensitive data or functionality.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, ensure that the Google OAuth provider component is configured with an explicit audience or clientId when mcpEnabled is true to enforce proper token audience validation.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- Date Reserved
- 2026-07-03T03:38:02.749Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a6c0df79c2644c7f8308762
Added to database: 07/31/2026, 02:52:39 UTC
Last enriched: 08/07/2026, 14:45:21 UTC
Last updated: 09/13/2026, 22:01:31 UTC
Views: 59
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.