data-metabase
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external Metabase instances, which constitutes a standard attack surface for indirect prompt injection if the source database or API response contains malicious instructions.
- Ingestion points: API responses and query results processed in
scripts/metabase_api.pyvia commands likerun-queryandexport-card-query. - Boundary markers: The skill includes detailed instructions for content validation and mutation inventories, though it does not use explicit delimiters for the agent's interpretation of raw data.
- Capability inventory: The skill has the ability to write files to the local system (using the
--outflag) and perform authenticated mutations (creating/updating cards and dashboards) on the Metabase instance. - Sanitization: Data is handled as structured JSON or CSV, relying on Metabase's native parameterization and security models for SQL execution.
Audit Metadata