CVE-2026-54602 FastGPT: Cross-team LLM request/response disclosure (IDOR) via /api/core/ai/record/getRecord
Authenticated users can read other teams' LLM prompts and responses by accessing a specific API endpoint without proper team scoping.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-54602?
CVE-2026-54602 is a high-severity missing authorization vulnerability in labring FastGPT, published on 7 Jul 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
FastGPT is a knowledge-based AI application platform. Prior to 4.15.0, GET /api/core/ai/record/getRecord authenticates the caller but loads LLM request and response traces only by requestId without team scoping, allowing 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.
Weakness: CWE-639
Which versions are affected by CVE-2026-54602?
How do I fix CVE-2026-54602?
No fix has been published for CVE-2026-54602 yet. Limit exposure of the affected software until one is available.
Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.
Is CVE-2026-54602 being exploited?
There is no known exploitation of CVE-2026-54602 in the wild and no public exploit code.
Sources
Also known as GHSA-6vx6-f72r-74cg.