Arbitrary file read via SQL blocklist gaps
Published Jul 9, 2026 · Updated Jul 10, 2026
SQL injection in SQLChatAgent before 0.64.0 allows remote attackers to read files from PostgreSQL hosts via crafted prompts. The _validate_query method lets SELECT calls such as pg_read_file pass its incomplete name-based regex blocklist and reach SQLAlchemy execution. Any caller or ingested data source able to shape LLM-generated SQL can trigger disclosure under the strict default configuration, while absolute-path access depends on the agent's database role.
Summary
What happened
SQL injection in SQLChatAgent before 0.64.0 allows remote attackers to read files from PostgreSQL hosts via crafted prompts. The _validate_query method lets SELECT calls such as pg_read_file pass its incomplete name-based regex blocklist and reach SQLAlchemy execution. Any caller or ingested data source able to shape LLM-generated SQL can trigger disclosure under the strict default configuration, while absolute-path access depends on the agent's database role.
The record
- CVE
- CVE-2026-50180
- Published
- Jul 9, 2026
- Updated
- Jul 10, 2026
- Vendor
- Langroid
- Product
- Langroid
- Classifications
- CWE-22, CWE-89, T1005
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 9, 2026CVE publishedPublication date reported by the CVE source.
- Jul 10, 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=< 0.64.0
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
- GHSA-pmch-g965-grmr PostgreSQL file-read 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