CVE-2026-54602
HighCVSS 7.1Exploitation Probability (EPSS)
Low risk13th percentile - higher than 13% of all known CVEs
Summary
In FastGPT before version 4.15.0, the GET /api/core/ai/record/getRecord endpoint authenticates the caller but loads LLM request and response traces only by requestId without team scoping. This allows any authenticated user to read another team's prompts, retrieved RAG chunks, and completions if the requestId is known.
Risk Assessment
The organization is at risk of leaking sensitive data processed by the LLM, including prompts and responses, which could lead to disclosure of trade secrets or personal data.
Recommendation
Immediately upgrade FastGPT to version 4.15.0 or later, which includes a fix for this vulnerability.
Original NVD description (English source)
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.