ETL Pipeline
Pass
Audited by Gen Agent Trust Hub on Jun 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest data from multiple external sources, creating an attack surface for indirect prompt injection (Category 8).
- Ingestion points: Data enters the agent's context through database queries (PostgreSQL, MySQL, MongoDB) and API integrations (Stripe, Salesforce, generic REST APIs) as defined in the
Source Connectorssection ofSKILL.md. - Boundary markers: The provided instructions and templates do not include explicit boundary markers or delimiters to isolate untrusted external data from the agent's internal logic.
- Capability inventory: The skill utilizes powerful tools including
postgres_query,mysql_query,mongodb_aggregate,bigquery_load, andsnowflake_api, which allow the agent to read from and write to production data environments. - Sanitization: While the
Transformation Layerincludes operational cleaning (handling nulls, deduplication), there are no specific security instructions for the agent to sanitize or ignore instructions potentially embedded within the data retrieved from external APIs or databases.
Audit Metadata