databricks-cost-leak-hunter

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text at runtime via the user-provided prompt (e.g., “databricks cost…”) and may also accept pasted config/spend input when databricks-workspace-mcp is absent, which constitutes attacker-controlled free text.