A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0… (CVE-2026-14540)
A Server-Side Request Forgery (SSRF) vulnerability exists in Google mcp-toolbox versions 0.3.0 through 1.4.0. The vulnerability arises because the HTTP client used by the toolbox does not enforce restrictive redirect policies or validate target IPs, allowing crafted requests to cause unauthorized internal or external requests. This can lead to information disclosure or unauthorized interactions with internal systems. The vulnerability has a CVSS score of 6.1, indicating a high severity level.
AI Analysis
Technical Summary
Google mcp-toolbox versions 0.3.0 through 1.4.0 contain an SSRF vulnerability in their generic HTTP source and tool components. Although baseline input sanitization is implemented, the underlying HTTP client (internal/sources/http/http.go) lacks a restrictive CheckRedirect policy and does not validate the IP addresses of redirection targets. This allows an attacker or malicious prompt to supply a crafted path parameter that triggers open redirects or destination swaps, causing the toolbox to follow redirects blindly and make unauthorized requests to internal or arbitrary external endpoints.
Potential Impact
The vulnerability can be exploited to coerce the mcp-toolbox into making unauthorized HTTP requests to internal or external systems. This may lead to limited confidentiality and integrity impacts, such as information disclosure or unauthorized interactions with backend services. There is no indication of availability impact. No known exploits are reported in the wild at this time.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no patch or official fix information is provided, users should monitor vendor communications for updates. Until a fix is available, avoid exposing the vulnerable components to untrusted inputs or untrusted networks where possible.
A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0… (CVE-2026-14540)
Description
A Server-Side Request Forgery (SSRF) vulnerability exists in Google mcp-toolbox versions 0.3.0 through 1.4.0. The vulnerability arises because the HTTP client used by the toolbox does not enforce restrictive redirect policies or validate target IPs, allowing crafted requests to cause unauthorized internal or external requests. This can lead to information disclosure or unauthorized interactions with internal systems. The vulnerability has a CVSS score of 6.1, indicating a high severity level.
CVSS v3.1
Score 6.1medium
Affected software
pkg:github/googleapis/mcp-toolboxRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
Google mcp-toolbox versions 0.3.0 through 1.4.0 contain an SSRF vulnerability in their generic HTTP source and tool components. Although baseline input sanitization is implemented, the underlying HTTP client (internal/sources/http/http.go) lacks a restrictive CheckRedirect policy and does not validate the IP addresses of redirection targets. This allows an attacker or malicious prompt to supply a crafted path parameter that triggers open redirects or destination swaps, causing the toolbox to follow redirects blindly and make unauthorized requests to internal or arbitrary external endpoints.
Potential Impact
The vulnerability can be exploited to coerce the mcp-toolbox into making unauthorized HTTP requests to internal or external systems. This may lead to limited confidentiality and integrity impacts, such as information disclosure or unauthorized interactions with backend services. There is no indication of availability impact. No known exploits are reported in the wild at this time.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no patch or official fix information is provided, users should monitor vendor communications for updates. Until a fix is available, avoid exposing the vulnerable components to untrusted inputs or untrusted networks where possible.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-3x3x-8ffg-ghcv
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-14540"]
- Ecosystems
- []
- Database Specific Severity
- HIGH
- Cvss Version
- 3.1
Threat ID: 6a77428ebf8831d539b07160
Added to database: 08/08/2026, 14:51:58 UTC
Last enriched: 08/08/2026, 15:07:31 UTC
Last updated: 08/09/2026, 00:41:12 UTC
Views: 2
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.
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.