CVE-2026-61643 labring CVE debrief

Who should care

Users of FastGPT, especially those with administrative privileges, should be aware of this vulnerability and take necessary actions to protect their systems. Affected operators and platforms should review and validate their deployments, and security teams should prioritize patching and monitoring.

Technical summary

The vulnerability exists in FastGPT versions from 4.14.17 to 4.15.0-beta5. An authenticated user can save a workflow node with a crafted tool ID, such as http-<victim_toolset_app_id>/<tool_name>, which allows access to the victim's private HTTP toolset. The normal toolset routes deny access, but the workflow save and runtime path do not apply the same authorization check. This allows unauthorized access to the victim's toolset through the /api/v2/chat/completions endpoint.

Defensive priority

Medium

Recommended defensive actions

• Update FastGPT to version 4.15.0-beta5 or later
• Restrict access to sensitive toolsets
• Monitor system logs for suspicious activity
• Implement additional authorization checks for workflow nodes
• Review compensating controls for exposed systems while remediation is scheduled and verified
• Check relevant monitoring, detection, and logs for exposed assets that need extra review
• Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record was published on 2026-07-15T18:16:49.510Z and last modified on 2026-07-20T16:17:06.297Z. The NVD entry is currently Deferred. Evidence is limited to public CVE and NVD information. Defenders should verify affected product deployments and review official advisories for validation.

Official resources