The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several CLI-based Python scripts (pipeline_orchestrator.py, data_quality_validator.py, etl_performance_optimizer.py) for managing data engineering workflows. The script scripts/pipeline_orchestrator.py utilizes the compile() function to validate the syntax of generated pipeline configurations (Airflow, Prefect, Dagster). While this is a common validation pattern in code generators, dynamic code manipulation is a sensitive capability that can be exploited if the inputs are not strictly controlled.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the processing of untrusted external data. Ingestion points: Data is read from files provided to the validation and optimization scripts. Boundary markers: None are employed to separate data from potential instructions within the files. Capability inventory: The skill allows for file system writes and dynamic code compilation. Sanitization: While type checking and schema validation are implemented, there is no specific logic to detect or sanitize malicious natural language instructions embedded within the data.
[EXTERNAL_DOWNLOADS]: The documentation references and provides instructions for installing multiple third-party packages and tools from public registries, including dbt, Airflow, Great Expectations, and OpenLineage. While these are industry-standard tools, users should ensure they are using trusted versions and secure environments.

senior-data-engineer