CVE-2026-25879

What it is

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access (e.g., PostgreSQL pg_execute_server_program, MySQL FILE, MSSQL xp_cmdshell), an attacker who can shape the agent's input — including indirectly via data returned to the LLM — can coerce execution of dialect-specific primitives such as `COPY ... FROM PROGRAM`, achieving RCE on the database host. Fixed in v0.63.0 by defaulting SQLChatAgent to a SELECT-only sqlglot-parsed statement allowlist with a dialect-aware dangerous-pattern blocklist; allow_dangerous_operations=True restores the previous unrestricted behavior for trusted deployments.

At a glance

Exploitability

Can be exploited over the network without logging in. High risk of data exposure, data tampering, service disruption.

Exploit odds

0.6% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-06-01 23:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-07-21 19:10 UTC Last updatedMost recent change to the record

Details

Published

2026-06-01 23:16 UTC

Last modified

2026-07-21 19:10 UTC

Exploit probability

0.6% · EPSS, next 30 days

Weakness

CWE-89 · SQL injection

Record status

Deferred

Attack profile CVSS 3.1 · 9.8

Attack vector

Network

Complexity

Low

Privileges needed

None

User interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High