The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs users to install the great_expectations package from the standard Python Package Index (PyPI).
[CREDENTIALS_UNSAFE]: The skill demonstrates secure credential handling by utilizing environment variable placeholders (${SLACK_WEBHOOK}) for Slack integrations instead of hardcoding sensitive tokens.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) within the quality_pipeline.py script.
Ingestion points: Data is ingested from external database validation results via the observed_value field in the generate_report method of DataQualityPipeline.
Boundary markers: The generated markdown report lacks delimiters or warnings to prevent the agent from interpreting embedded data as instructions.
Capability inventory: The skill performs database read operations and generates text-based reports that may be consumed by an agent; it also supports raising exceptions based on validation failures.
Sanitization: There is no evidence of escaping or sanitizing the observed data values before they are interpolated into the final markdown report.

data-quality-frameworks