bronze-layer-setup

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and interprets external/untrusted data sources — e.g., the mandatory pattern to "read the customer's source schema CSV from context/Wanderbricks_Schema.csv" (SKILL.md Step 2 and the CSV parsing snippet) and the documented Approach C and scripts/copy_from_source.py which load CSVs and JDBC external databases — and uses those contents to generate DDLs and drive job actions, so untrusted content can materially influence behavior.