The Agent Skills Directory

[SAFE]: The skill provides high-quality security guidance, explicitly instructing users to avoid exposing service_role keys, use security_invoker for views, and implement proper Row Level Security (RLS) patterns.
[EXTERNAL_DOWNLOADS]: The skill references several external resources for documentation and changelogs, such as https://supabase.com/changelog.md and https://supabase.com/docs/guides/security/product-security.md. These are official domains belonging to the vendor (Supabase) and are considered safe.
[COMMAND_EXECUTION]: The skill provides examples of supabase CLI commands and curl for troubleshooting the MCP server. These are standard developer operations and do not represent a security risk within the context of the skill's purpose.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external documentation and changelogs. While this presents a surface for indirect prompt injection, the instructions emphasize using official Supabase sources, and the risk is mitigated by the agent's internal safety guardrails. The severity is low.

supabase