What’s Vulnerable › Vulnerabilities

CVE-2026-54602: FastGPT: Cross-team LLM request/response disclosure (IDOR) via /api/core/ai/record/getRecord

• Severity: high (CVSS 7.1 v4.0)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-07-07 · updated 2026-10-25
• Weakness: CWE-639

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.

Affected products

• labring FastGPT: before 4.15.0

References

• https://github.com/labring/FastGPT/commit/60c62b7af8269c826885b541bb56e6e5c424c11a
• https://github.com/labring/FastGPT/security/advisories/GHSA-6vx6-f72r-74cg

Get alerted when CVE-2026-54602 or the next vulnerability affects your stack