The SQLChatAgent SQL-injection mitigation, with default allow_dangerous_operations=False, combines a raw-text regex blocklist (_DANGEROUS_SQL_PATTERNS) with a sqlglot SELECT-only statement allowlist. The blocklist entries that target callable functions require the function name to be immediately followed by \s*(. PostgreSQL accepts the same call with the name separated from ( by a quoted identifier, an inline comment, or schema qualification. These forms evade the regex, still parse as SELECT, and execute the same …
Langroid is vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its TableChatAgent and VectorStore capabilities. When these agents evaluate LLM-generated tool messages with full_eval=True, they attempt to sandbox the execution by explicitly setting locals to an empty dictionary {} inside Python's eval() function. However, this relies on an incomplete understanding of Python's execution model. Because builtins is not explicitly scrubbed from the globals dictionary mapping, …
Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt injection (direct user input or indirect content the agent reads back via RAG), so an attacker who can influence the prompt can read or destroy all graph data and, when APOC or dbms.security procedures are enabled on the server, achieve OS-command and filesystem …
A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True.
SQLChatAgent in langroid ships a _validate_query defense-in-depth layer whose _DANGEROUS_SQL_PATTERNS regex blocklist enumerates dangerous SQL primitives by specific function name. The list misses the canonical PostgreSQL filesystem-disclosure family pg_read_file(), pg_stat_file(), pg_ls_logdir(), pg_ls_waldir(), pg_current_logfile() (and similar SELECT-shaped functions in the same family). It also leaves SQL Server OPENDATASOURCE and SQLite ATTACH '<file>' AS x (DATABASE keyword omitted) unblocked. An attacker able to shape the LLM's generated SQL (directly via prompt input …
Langroid's ReadFileTool and WriteFileTool appear to treat curr_dir as the intended working-directory boundary for file operations. However, the tools only change the process working directory to curr_dir and then operate on the user-supplied file_path without resolving and enforcing that the final path remains inside curr_dir. As a result, a tool caller can supply path traversal sequences such as ../secret.txt to read files outside the configured current directory, or ../written_by_tool.txt to …
Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid Affected Scope langroid < 0.63.0 Vulnerability Description 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 …
Affected Scope langroid <= 0.59.31 Vulnerability Description CVE-2025-46724 fix bypass: TableChatAgent can call pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to _literal_ok() returning False instead of raising UnsafeCommandError on invalid input, combined with unrestricted access to dangerous dunder attributes (init, globals, builtins). This allows chaining whitelisted DataFrame methods to leak the eval builtin …