9.8
/ 10
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Description
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.
AI Analysis
Prompt injection vulnerability in Langroid's SQLChatAgent, allowing remote code execution on the database host
Basic Information
ID
CVE-2026-25879
Source
GitHub_M
Published
Jun 1, 2026 at 22:27
Affected Product
Vendor
langroid
Product
langroid
Version
< 0.63.0
Affected Versions
langroid langroid < 0.63.0
CWE Classification
AI Assessment
AI Score
9.8 / 10
AI Severity
Critical
Vendor
Langroid
Product
Langroid
Version
< 0.63.0