CVE-2026-25879
9.8 CRITICALLangroid is a framework for building large-language-model-powered applications
Published: 2026-06-01 · Last updated: 2026-06-02
Severity and scoring
- CVSS
- 9.8 CRITICAL
- Vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- CWE
- CWE-89, CWE-94
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.
Source: NVD
References
Related CVEs
Same CWE
- CVE-2026-50223 — Improper Control of Generation of Code ('Code Injection') vulnerability in Apache OFBiz allows a low-privileged authenticated user with C...
- CVE-2026-53474 — A flaw was found in migration-planner (9.6 CRITICAL)
- CVE-2026-45558 — Roxy-WI is a web interface for managing Haproxy, Nginx, Apache and Keepalived servers (9.9 CRITICAL)
- CVE-2026-52758 — Ghidra before 12.1 contains a SQL injection vulnerability in BSim filter types that concatenate user-supplied values directly into SQL qu... (8.8 HIGH)
- CVE-2026-49498 — Ghidra 11.0 before 12.1 contains a SQL injection vulnerability in the changePassword() method of PostgresFunctionDatabase that fails to e... (8.8 HIGH)