PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-54602 labring CVE debrief

CVE-2026-54602 is a vulnerability in FastGPT, a knowledge-based AI application platform. Prior to version 4.15.0, the platform allows any authenticated user to read another team's prompts, retrieved RAG chunks, and completions if the requestId is known. This issue is fixed in version 4.15.0. The vulnerability exists due to insufficient team scoping in the GET /api/core/ai/record/getRecord endpoint, allowing unauthorized access to sensitive information.

Vendor
labring
Product
FastGPT
CVSS
HIGH 7.1
CISA KEV
Not listed in stored evidence
Original CVE published
2026-07-07
Original CVE updated
2026-07-07
Advisory published
2026-07-07
Advisory updated
2026-07-07

Who should care

Users of FastGPT, especially those with multiple teams, should be aware of this vulnerability and ensure they are running version 4.15.0 or later to prevent unauthorized access to sensitive information. This includes operators, platform administrators, vulnerability management teams, and security teams.

Technical summary

The vulnerability exists in the GET /api/core/ai/record/getRecord endpoint of FastGPT, a knowledge-based AI application platform. Prior to version 4.15.0, this endpoint authenticates the caller but loads LLM request and response traces only by requestId without team scoping. This allows any authenticated user to access another team's data if the requestId is known. The issue is fixed in version 4.15.0 of FastGPT. Affected product deployments should be reviewed for exposure, and owners should plan for vendor-supported updates or mitigations through normal change control. Compensating controls should be reviewed for exposed systems while remediation is scheduled and verified.

Defensive priority

High priority should be given to upgrading to FastGPT version 4.15.0 or later, reviewing and restricting access to sensitive information, and monitoring for suspicious activity. Compensating controls should be reviewed for exposed systems while remediation is scheduled and verified. Relevant monitoring, detection, and logs should be checked for exposed assets that need extra review. Exceptions should be tracked, and remediated assets should be retested and closed only after evidence is documented. Asset inventory and source tracking are also recommended. Rollback/change windows should be considered if necessary.

Recommended defensive actions

  • Upgrade to FastGPT version 4.15.0 or later
  • Review and restrict access to sensitive information
  • Monitor for suspicious activity
  • 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
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The CVE record was published on 2026-07-07T22:16:53.217Z and has not been modified since then. The NVD entry is currently 7.1 HIGH. This information is based on the NVD entry and the CVE record. The vulnerability affects FastGPT, a knowledge-based AI application platform, and is fixed in version 4.15.0.

Official resources

AI-assisted PatchSiren debrief based on the supplied source corpus. The CVE record was published on 2026-07-07T22:16:53.217Z and has not been modified since then.