supabase
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external documentation from Supabase and GitHub, which presents a potential surface for indirect instructions to influence agent actions.\n
- Ingestion points: Documentation fetching via
search_docsand markdown conversion of Supabase URLs as described inSKILL.md.\n - Capability inventory: The agent is granted capabilities to execute SQL via
execute_sqland manage the file system using the Supabase CLI.\n - Boundary markers: Instructions do not explicitly require the use of delimiters or ignore-instructions for retrieved documentation content.\n
- Sanitization: There is no mention of filtering or sanitizing documentation content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill provides detailed instructions for executing Supabase CLI commands (
supabase) to manage database schema changes, migrations, and project health checks.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and submits feedback to official Supabase infrastructure, includingsupabase.com,mcp.supabase.com, and thesupabase/agent-skillsrepository on GitHub. These are recognized as trusted vendor resources.
Audit Metadata