Skip to content

Hide Navigation Hide TOC

SQL Injection via Natural Language Agent Interface - ATR-2026-00522 (f84553c3-352a-5b05-809b-096021020921)

Detects SQL injection attempts made through natural language to an AI agent that translates user intent into database queries. Covers both explicit SQL syntax and natural-language filter-bypass requests. Seen in promptfoo redteam sql-injection plugin (8 samples). The original auto-regex learned specific sentence patterns from the corpus. This rule replaces those with structural SQL-injection patterns that generalize across payloads: (A) DDL/DML injection: DROP, DELETE, TRUNCATE, UNION SELECT, INSERT INTO, UPDATE ... SET; (B) Tautology OR injection: OR N=N or OR col!=N patterns that short-circuit WHERE clauses; (C) SQL comment terminator (--) following injection payload; (D) xp_cmdshell stored procedure execution; (E) information_schema schema discovery queries; (F) Natural language filter bypass: "remove/ignore/bypass the filter/restriction/access control"; (G) Natural language authorization bypass: "regardless of department/role/permission". Any one condition is sufficient to trigger. Both technical SQL syntax and social-engineering bypass styles are covered.

Cluster A Galaxy A Cluster B Galaxy B Level
SQL Injection via Natural Language Agent Interface - ATR-2026-00522 (f84553c3-352a-5b05-809b-096021020921) Agent Threat Rules LLM Plugin Compromise (adbb0dd5-ff66-4b2f-869f-bfb3fdb45fc8) MITRE ATLAS Attack Pattern 1