metabase-react-sdk-setup

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to interact with a Metabase instance, including fetching session properties, enabling embedding settings, and performing searches for dashboards and database candidates. It also executes local shell commands to write configuration to .env.metabase and install dependencies via npm or yarn.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from a remote Metabase API (dashboard lists, table candidates) and fetches documentation from an external source (llms.txt on metabase.com). While these sources are generally trusted or internal to the user's infrastructure, the ingestion of this data could technically serve as a vector for instructions, though the risk is assessed as low due to the structured nature of the API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:52 AM