data-engineering-data-pipeline
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core purpose is to design and implement data pipelines that ingest content from external, untrusted sources such as PostgreSQL databases and Kafka streams. This introduces a vulnerability surface where malicious instructions embedded in the data could influence the agent's execution logic.
- Ingestion points: External database queries (via connection strings) and Kafka consumers as described in the implementation instructions and code examples in SKILL.md.
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or 'ignore' directives when processing the ingested data.
- Capability inventory: The described workflows include database extraction, code execution (Spark/dbt), and writing to cloud storage environments (S3/Delta Lake).
- Sanitization: The instructions recommend schema validation and dead letter queues for records failing structural checks, though these are not specifically designed to filter prompt injection content.
Audit Metadata