supabase
Pass
Audited by Gen Agent Trust Hub on Jun 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and configuration from official Supabase GitHub repositories and domains (e.g., supabase.com, mcp.supabase.com). These are well-known, recognized sources used for up-to-date guidance.\n- [COMMAND_EXECUTION]: The skill utilizes the Supabase CLI for database operations and migrations. These commands are standard for project management and are intended for execution in the user's local development environment.\n- [PROMPT_INJECTION]: The skill processes data from external documentation and project-specific files.\n- Ingestion points: Documentation URLs and the search_docs tool.\n- Boundary markers: None explicitly defined for external content.\n- Capability inventory: SQL execution (execute_sql), CLI subprocess calls (supabase commands), and pull request management (github-merge-pull-request).\n- Sanitization: None specified for retrieved documentation content.\n- Analysis: An indirect prompt injection surface exists via documentation ingestion; however, the risk is mitigated by the use of official vendor sources and the inclusion of a robust security checklist for the agent to follow.
Audit Metadata