skills/sarthib7/agentsmith/supabase/Gen Agent Trust Hub

supabase

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the official Supabase CLI for database operations and migrations. It also includes a curl command for checking the availability of the Supabase MCP server, which is a standard diagnostic procedure for this service.
  • [EXTERNAL_DOWNLOADS]: The skill references and retrieves documentation from well-known, official Supabase domains (supabase.com, mcp.supabase.com) and its public GitHub repositories. These operations are essential for maintaining up-to-date knowledge of the platform's features and security guidelines.
  • [PROMPT_INJECTION]: The skill processes information from external documentation and user tasks, which presents a surface for indirect prompt injection. However, the risk is mitigated because the skill exclusively targets official documentation and provides specific instructions for verifying changes and following safety checklists.
  • Ingestion points: Documentation retrieved through the MCP search_docs tool and direct fetching of markdown files from official Supabase URLs.
  • Boundary markers: Not explicitly defined in the instruction set.
  • Capability inventory: The skill can execute SQL queries, manage migration files, and interact with project configuration through the CLI.
  • Sanitization: Relies on the standard safety protocols of the documentation retrieval tools and the Supabase CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:04 AM
Security Audit — agent-trust-hub — supabase