# CVE-2026-102242: Google MCP Toolbox for Databases path traversal via symlink

Source: https://junglewise.ai/threats/cve-2026-102242-improper-link-resolution-cwe-59-cwe-22-in-the-allowedlocalroots  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-29. Updated: 2026-09-29  
License: CC BY 4.0 with a link back

CVE-2026-102242 · Severity: info · Published 2026-09-29

Google's MCP Toolbox for Databases fails to properly validate directory boundaries when symbolic links are present, allowing authenticated attackers to access or modify files outside their permitted directories. An attacker with tool execution permissions can use symbolic links to bypass directory restrictions and read or overwrite sensitive files on the system.

Technologies: [Google MCP Toolbox for Databases](https://junglewise.ai/threats/technologies/mcp-toolbox-for-databases). Vendors: [Google](https://junglewise.ai/threats/vendors/google).

## Quick answers

**Is CVE-2026-102242 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-102242 being exploited in the wild.

**How severe is CVE-2026-102242?** Informational severity, published 29 September 2026.

**Which products and versions are affected?** Google MCP Toolbox for Databases 1.2.0 through 1.9.0.

**Is there a fix for CVE-2026-102242?** A patch was published on 2026-08-20. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-102242 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-102242?** Check whether you run Google MCP Toolbox for Databases at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability exists in the allowedLocalRoots path validation logic (CWE-59/CWE-22), which performs lexical directory checks without first resolving symbolic links. An authenticated attacker with tool execution permissions can craft symbolic links within permitted root directories to point to arbitrary locations outside those boundaries, gaining unauthorized access to or modification of local files. A fix resolving symbolic links before enforcing path boundaries was merged in August 2026.

## Affected products

- Google MCP Toolbox for Databases 1.2.0 through 1.9.0

## Timeline

- 2026-09-29: disclosed
- 2026-08-20: patched

## References

- [https://github.com/googleapis/mcp-toolbox/pull/3810](https://github.com/googleapis/mcp-toolbox/pull/3810)

## Related threats

- [Google MCP Toolbox SSRF and credential exfiltration in FHIR fetch tool](https://junglewise.ai/threats/cve-2026-16481-google-mcp-toolbox-ssrf-and-credential-exfiltration-in-fhir-fetch)
- [Google MCP Toolbox SQL injection in BigQuery forecasting tool](https://junglewise.ai/threats/cve-2026-15829-google-mcp-toolbox-sql-injection-in-bigquery-forecasting-tool)
- [Google MCP Toolbox path traversal in HTTP tool URL builder](https://junglewise.ai/threats/cve-2026-11720-google-mcp-toolbox-path-traversal-in-http-tool-url-builder)
- [Google MCP Toolbox for Databases authorization bypass in protocol handlers](https://junglewise.ai/threats/cve-2026-11719-google-mcp-toolbox-for-databases-authorization-bypass-in-protocol)
- [Google MCP Toolbox authentication bypass in validateOpaqueToken](https://junglewise.ai/threats/cve-2026-11718-google-mcp-toolbox-authentication-bypass-in-validateopaquetoken)