FastGPT versions before 4.14.10.3 contain an SSRF vulnerability in the /api/core/app/mcpTools/runTool endpoint. This endpoint accepts arbitrary URLs without authentication, and the internal IP filtering function (isInternalAddress()) only blocks private IPs if the CHECK_INTERNAL_IP environment variable is set to true, which is not the default configuration. Consequently, unauthenticated attackers can leverage this to perform SSRF attacks targeting internal network resources. The vulnerability is addressed in FastGPT version 4.14.10.3.

An unauthenticated attacker can exploit this SSRF vulnerability to make requests from the FastGPT server to internal network resources that are otherwise inaccessible externally. This could potentially expose sensitive internal services or data. The CVSS score of 5.3 reflects a medium impact primarily on confidentiality. There is no indication of integrity or availability impact. No known exploits are reported in the wild at this time.

Upgrade FastGPT to version 4.14.10.3 or later, where this SSRF vulnerability is fixed. Until the upgrade is applied, consider enabling the CHECK_INTERNAL_IP setting to true to enforce internal IP blocking, though this is a temporary measure and may not fully mitigate all risks. Monitor vendor advisories for any additional guidance. No other official remediation level is provided.