Authenticated RCE via unvalidated LLM-generated SQL
Published May 5, 2026 · Updated May 5, 2026
Prompt injection in FIT2CLOUD SQLBot 1.7.0 and earlier allows remote authenticated users to execute arbitrary SQL through crafted chat questions. The sql_user_question function inserts the question into the LLM prompt without filtering, while check_sql accepts the returned SQL and exec_sql passes it directly to the database driver. A valid account and selected PostgreSQL data source are required; COPY FROM PROGRAM then executes operating-system commands with the database service account.
Summary
What happened
Prompt injection in FIT2CLOUD SQLBot 1.7.0 and earlier allows remote authenticated users to execute arbitrary SQL through crafted chat questions. The sql_user_question function inserts the question into the LLM prompt without filtering, while check_sql accepts the returned SQL and exec_sql passes it directly to the database driver. A valid account and selected PostgreSQL data source are required; COPY FROM PROGRAM then executes operating-system commands with the database service account.
The record
- CVE
- CVE-2026-33324
- Published
- May 5, 2026
- Updated
- May 5, 2026
- Vendor
- KubeOperator
- Product
- SQLBot
- Classifications
- T1190
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- May 5, 2026CVE publishedPublication date reported by the CVE source.
- May 5, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 1.7.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Vendor advisory PostgreSQL command-execution proof of conceptfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo