carto-explore-datawarehouse
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation describes the use of a vendor-provided CLI tool (
carto) for browsing connection hierarchies and describing table schemas. These commands are integral to the skill's intended purpose of data discovery within the CARTO environment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests metadata, such as table and column names, from external data warehouses (e.g., BigQuery, Snowflake). While this represents a potential ingestion surface for untrusted data, the risk is negligible as the data is used for structural exploration rather than logical control flow.
- [SAFE]: The skill follows least-privilege principles by focusing on inspection and discovery. It explicitly marks modification tasks (creating/updating named sources) as out of scope, reducing the attack surface.
Audit Metadata