CVE-2026-33324

Affects: prompt injection, large language model

CVSS
HIGH · 8.8 v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Published
2026-05-05
Weakness
CWE-89
Source
nvd.nist.gov/vuln/detail/CVE-2026-33324

Description

SQLBot is an intelligent Text-to-SQL system based on large language models and RAG. In versions 1.7.0 and earlier, the Text2SQL chat interface is vulnerable to prompt injection. The user-provided question parameter is directly concatenated into the LLM prompt without filtering or escaping, and the SQL extracted from the LLM response is executed against the database without validation or sanitization. An authenticated attacker can craft a malicious question to manipulate the LLM into generating and executing arbitrary SQL statements. When connected to a PostgreSQL data source, this can lead to remote code execution via COPY FROM PROGRAM. This issue has been fixed in version 1.7.1.

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-2026-33324 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