setting-up-a-data-warehouse-source

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes metadata and error messages from external databases via the external-data-sources-db-schema tool (SKILL.md), which constitutes an indirect prompt injection surface. 1. Ingestion points: External table metadata and connection errors from the db-schema tool. 2. Boundary markers: Absent. 3. Capability inventory: external-data-sources-create and external-data-sources-create-webhook-create (SKILL.md). 4. Sanitization: Absent; the skill instructs the agent to show error messages verbatim to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:53 PM