CVE-2026-44284: medium-severity vulnerability in labring FastGPT
FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 6.3epss 0.2%
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
Affected products
labring · FastGPTRelated CVEs — labring FastGPT
In the same product, most dangerous first.
CVE-2026-42302CRITICALFastGPT: Unauthenticated Remote Code Execution (RCE) via code-server Misconfiguration in agent-sandboxEPSS 0.7%CVE-2026-40351CRITICALFastGPT: NoSQL Injection in loginByPassword leads to Authentication BypassEPSS 0.6%CVE-2025-49131MEDIUMFastGPT Sandbox Vulnerable to Sandbox BypassEPSS 0.5%CVE-2026-55418HIGHFastGPT: S3 presign/read handlers do not bind the object key to the caller's team (cross-team file disclosure)EPSS 0.5%CVE-2026-68929CRITICALFastGPT: Unauthenticated WeChat channel hijack and denial of service via shareId-only authorizationEPSS 0.4%CVE-2026-34162CRITICALFastGPT: Unauthenticated SSRF via httpTools Endpoint Leads to Internal API Key TheftEPSS 0.4%