CVE-2025-69285

Affects: large language model

CVSS: MEDIUM · 6.1v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N
Published: 2026-01-21
Weakness: CWE-306
Source: nvd.nist.gov/vuln/detail/CVE-2025-69285

Description

SQLBot is an intelligent data query system based on a large language model and RAG. Versions prior to 1.5.0 contain a missing authentication vulnerability in the /api/v1/datasource/uploadExcel endpoint, allowing a remote unauthenticated attacker to upload arbitrary Excel/CSV files and inject data directly into the PostgreSQL database. The endpoint is explicitly added to the authentication whitelist, causing the TokenMiddleware to bypass all token validation. Uploaded files are parsed by pandas and inserted into the database via to_sql() with if_exists=‘replace’ mode. The vulnerability has been fixed in v1.5.0. No known workarounds are available.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-69285 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming