superset-dashboard-automation
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing data from external sources. * Ingestion points: Data is retrieved from Supabase, Odoo PostgreSQL, and CSV files as described in the Quick Start and Workflow sections of SKILL.md. * Boundary markers: There are no delimiters or protective instructions provided to distinguish legitimate data from potential instructions within the processed datasets. * Capability inventory: The agent is instructed to write and execute SQL queries, create datasets, and manage dashboard configurations, which are high-impact operations. * Sanitization: No data sanitization or validation steps are included in the workflows for processing external content.
Audit Metadata