Remote code execution via unrestricted LLM-generated SQL
Published Jun 1, 2026 · Updated Jun 1, 2026
SQL injection in Langroid SQLChatAgent before 0.63.0 allows remote attackers to execute commands on a privileged database host. The run_query tool passes LLM-generated SQL influenced by direct or indirect prompt injection to the database without restricting statement types or dangerous primitives. Command execution requires the configured database role to expose an operating-system or filesystem primitive; otherwise the attacker retains only the role's database permissions.
Summary
What happened
SQL injection in Langroid SQLChatAgent before 0.63.0 allows remote attackers to execute commands on a privileged database host. The run_query tool passes LLM-generated SQL influenced by direct or indirect prompt injection to the database without restricting statement types or dangerous primitives. Command execution requires the configured database role to expose an operating-system or filesystem primitive; otherwise the attacker retains only the role's database permissions.
The record
- CVE
- CVE-2026-25879
- Published
- Jun 1, 2026
- Updated
- Jun 1, 2026
- Vendor
- Langroid
- Product
- Langroid
- Classifications
- CWE-94, CWE-89, CWE-1427, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 1, 2026CVE publishedPublication date reported by the CVE source.
- Jun 1, 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=< 0.63.0
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
- Embedded PostgreSQL COPY FROM PROGRAM proof of conceptproof of concept · 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