CVE-2026-32622

Published Mar 19, 2026

Last updated a month ago

CVSS high 8.6

Overview

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.
Source
security-advisories@github.com
NVD status
Analyzed
Products
sqlbot

Risk scores

CVSS 4.0

Type
Secondary
Base score
8.6
Impact score
-
Exploitability score
-
Vector string
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Severity
HIGH

CVSS 3.1

Type
Primary
Base score
8.8
Impact score
5.9
Exploitability score
2.8
Vector string
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Severity
HIGH

Weaknesses

security-advisories@github.com
CWE-20

Social media

Hype score
Not currently trending

Configurations

Related CVEs

  1. SQLBot is an intelligent data query system based on a large language model and RAG. Versions prior to 1.7.0 contain a critical SQL Injection vulnerability in the /api/v1/datasource/uploadExcel endpoint that enables Remote Code Execution (RCE), allowing any authenticated user (even the lowest-privileged) to fully compromise the backend server. The root cause is twofold: Excel Sheet names are concatenated directly into PostgreSQL table names without sanitization (datasource.py#L351), and those table names are embedded into COPY SQL statements via f-strings instead of parameterized queries (datasource.py#L385-L388). An attacker can bypass the 31-character Sheet name limit using a two-stage technique—first uploading a normal file whose data rows contain shell commands, then uploading an XML-tampered file whose Sheet name injects a TO PROGRAM 'sh' clause into the SQL. Confirmed impacts include arbitrary command execution as the postgres user (uid=999), sensitive file exfiltration (e.g., /etc/passwd, /etc/shadow), and complete PostgreSQL database takeover. This issue has been fixed in version 1.7.0.•CVE-2026-32950
  2. SQLBot is an intelligent data query system based on a large language model and RAG. Versions prior to 1.7.0 contain a Server-Side Request Forgery (SSRF) vulnerability that allows an attacker to retrieve arbitrary system and application files from the server. An attacker can exploit the /api/v1/datasource/check endpoint by configuring a forged MySQL data source with a malicious parameter extraJdbc="local_infile=1". When the SQLBot backend attempts to verify the connectivity of this data source, an attacker-controlled Rogue MySQL server issues a malicious LOAD DATA LOCAL INFILE command during the MySQL handshake. This forces the target server to read arbitrary files from its local filesystem (such as /etc/passwd or configuration files) and transmit the contents back to the attacker. This issue was fixed in version 1.7.0.•CVE-2026-32949
  3. A vulnerability was found in Dataease SQLBot up to 1.5.1. This impacts the function validateEmbedded of the file backend/apps/system/middleware/auth.py of the component JWT Token Handler. Performing a manipulation results in improper verification of cryptographic signature. The attack can be initiated remotely. The attack is considered to have high complexity. The exploitability is said to be difficult. The exploit has been made public and could be used. A comment in the source code warns users about using this feature. The vendor was contacted early about this disclosure.•CVE-2025-15598
  4. A vulnerability has been found in Dataease SQLBot up to 1.4.0. This affects an unknown function of the file backend/apps/system/api/assistant.py of the component API Endpoint. Such manipulation leads to improper access controls. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. Upgrading to version 1.5.0 mitigates this issue. The name of the patch is d640ac31d1ce64ce90e06cf7081163915c9fc28c. Upgrading the affected component is recommended. Multiple endpoints are affected. The vendor was contacted early about this disclosure.•CVE-2025-15597
  5. 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.•CVE-2025-69285

References

Sources include official advisories and independent security research.