CVE-2026-25879: Langroid is a framework for building large-language-model-powered applications. Prior to version 0.6…
- Occurred
- Jun 1, 2026
- Published
- Jun 1, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-25879
- cvss:CRITICAL
- agent-fail:injection-indirect
- agent-fail:authorization
- agent-cause:missing-guardrail
- agent-cause:prompt-design
Classification
Rationale: Langroid SQLChatAgent vulnerability allows prompt injection leading to remote code execution on database hosts.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8