setting-up-a-data-warehouse-source
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata (table and column names) from external databases via the external-data-sources-db-schema tool to build configuration payloads.
- Ingestion points: Metadata from the external-data-sources-db-schema tool response.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions in the metadata.
- Capability inventory: The skill uses tools like external-data-sources-create and external-data-sources-setup to apply configurations.
- Sanitization: The instructions do not specify validation or sanitization of the external metadata before use.
Audit Metadata