CVE-2026-25879: critical vulnerability in langroid
Langroid has Prompt to SQL Injection, Leading to RCE
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
28Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 9.8epss 0.6%
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.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected products
langroid · langroidRelated CVEs — langroid
In the same product, most dangerous first.
CVE-2026-54769CRITICALLangroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgentEPSS 0.9%CVE-2025-46724CRITICALLangroid has a Code Injection vulnerability in TableChatAgentEPSS 0.8%CVE-2026-25481CRITICALLangroid has WAF Bypass Leading to RCE in TableChatAgentEPSS 0.7%CVE-2026-50180HIGHLangroid: SQLChatAgent _validate_query blocklist misses pg_read_file family enabling arbitrary file readEPSS 0.7%CVE-2025-46726HIGHLangroid Vulnerable to XXE Injection via XMLToolMessageEPSS 0.7%CVE-2026-54760CRITICALLangroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file callsEPSS 0.6%