supabase-automation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to add a third-party MCP server endpoint (
https://rube.app/mcp) to their client configuration. - [COMMAND_EXECUTION]: The skill provides tools for executing arbitrary SQL queries (
SUPABASE_BETA_RUN_SQL_QUERY) which allows direct manipulation of database systems. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Supabase databases, creating an attack surface where embedded instructions could influence agent behavior.
- Ingestion points: Table data and project metadata retrieved via
SUPABASE_SELECT_FROM_TABLEandSUPABASE_LIST_TABLESas described inSKILL.md. - Boundary markers: There are no instructions provided to the agent to treat external data as untrusted or to use specific delimiters.
- Capability inventory: The skill possesses high-privilege capabilities including database writes, SQL execution, and retrieval of service-role API keys.
- Sanitization: The skill does not define any sanitization or validation protocols for the external data it processes.
Audit Metadata