CVE-2026-32622

SQLBot: Remote Code Execution via Terminology Poisoning

Published Mar 19, 2026 CVSS 4.0 · 8.6 High EPSS < 1% KEV · Not listed
Description
SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology, unsanitized storage of terminology descriptions containing dangerous payloads, and a lack of semantic fencing when injecting terminology into the LLM's system prompt. Together, these flaws allow an attacker to hijack the LLM's reasoning to generate malicious PostgreSQL commands (e.g., COPY ... TO PROGRAM), ultimately achieving Remote Code Execution on the database or application server with postgres user privileges. The issue is fixed in v1.6.0.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Fit2cloud
Fit2cloud sqlbot
CPEs cpe:2.3:a:fit2cloud:sqlbot:*:*:*:*:*:*:*:*
Vendors & Products Fit2cloud
Fit2cloud sqlbot
Metrics cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H'}

Type Values Removed Values Added
First Time appeared Dataease
Dataease sqlbot
Vendors & Products Dataease
Dataease sqlbot
Type Values Removed Values Added
Description SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology, unsanitized storage of terminology descriptions containing dangerous payloads, and a lack of semantic fencing when injecting terminology into the LLM's system prompt. Together, these flaws allow an attacker to hijack the LLM's reasoning to generate malicious PostgreSQL commands (e.g., COPY ... TO PROGRAM), ultimately achieving Remote Code Execution on the database or application server with postgres user privileges. The issue is fixed in v1.6.0.
Title SQLBot: Remote Code Execution via Terminology Poisoning
Weaknesses CWE-20
CWE-74
CWE-77
CWE-862
References
Metrics cvssV4_0

{'score': 8.6, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N'}

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Mar 24, 2026, 1:40 AM
Reserved
Mar 12, 2026, 3:29 PM
Status
Analyzed
Published
Mar 19, 2026, 9:17 PM
Modified
Jun 17, 2026, 10:36 AM