The Agent Skills Directory

[SAFE]: The skill provides legitimate guidance for data architecture and pipeline development. It proactively includes safety measures such as enforcing least-privilege access, encrypting data at rest and in transit, and implementing audit logging.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external sources, which inherently introduces a surface for indirect prompt injection if the ingested data contains adversarial instructions.
Ingestion points: The skill interacts with external data sources including Apache Kafka, S3, BigQuery, and various third-party APIs (SKILL.md).
Boundary markers: Instructions recommend defining data contracts and SLAs to establish expectations for incoming data (SKILL.md).
Capability inventory: The skill possesses capabilities for data processing using Python, Scala, and Spark, which typically execute in environments with file system and network access (SKILL.md).
Sanitization: The skill mandates the use of data quality frameworks like Great Expectations and explicitly instructs the user to validate data before writing to production sinks (SKILL.md).

data-engineer