Data Engineer
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources which creates an attack surface for indirect prompt injection.
- Ingestion points: Data is read from JSON files (source_path) and Kafka topics (stream_bronze_orders) within the SKILL.md code templates.
- Boundary markers: The provided instructions do not include delimiters or specific instructions to the agent to ignore potential instructions embedded in the ingested data.
- Capability inventory: The skill utilizes Spark and Delta Lake APIs which have the capability to write and modify files on the system or cloud storage (e.g., '.save(bronze_table)') and perform network operations via Kafka connectivity.
- Sanitization: There are no explicit data validation or sanitization steps mentioned to filter out instructions from the raw data.
Audit Metadata