sql-server-table-reconciliation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill actively connects to user-specified source and target SQL Server instances and executes queries (see scripts/reconcile.py: resolve_tables, extract_table, extract_hashes and schema/data queries like "SELECT * FROM {table}" and INFORMATION_SCHEMA lookups), therefore ingesting arbitrary/untrusted database content that the agent reads and uses to drive reconciliation decisions.