The Agent Skills Directory

[DYNAMIC_EXECUTION]: The script scripts/pipeline_orchestrator.py utilizes the compile() function within the validate methods of the AirflowGenerator, PrefectGenerator, and DagsterGenerator classes. This function is used to perform syntax checks on generated pipeline code strings at runtime, which is a form of dynamic execution.
[INDIRECT_PROMPT_INJECTION]: The skill defines tools like scripts/data_quality_validator.py and scripts/etl_performance_optimizer.py that ingest data from external files (CSV, JSON, JSONL, SQL).
Ingestion points: The DataLoader.load method in scripts/data_quality_validator.py and file-reading arguments in scripts/etl_performance_optimizer.py are the primary points where untrusted data enters the agent context.
Boundary markers: The scripts do not implement specific delimiters or 'ignore' instructions for the data being processed.
Capability inventory: The skill includes capabilities to write files to the local system through scripts/pipeline_orchestrator.py and perform statistical analysis on local data.
Sanitization: While the scripts perform type and schema validation, they lack sanitization against instructions embedded within the data that might influence agent behavior.

senior-data-engineer