← back
CVE-2026-54602highCWE-639

FastGPT: Cross-team LLM request/response disclosure (IDOR) via /api/core/ai/record/getRecord

21Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 7.1epss 0.2%
exploitation probability
0.2%top 87% of all CVEs
observed exploitation
nono source reports it
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
Affected products
labring · FastGPT