The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell utilities such as ls, cat, mkdir, and head to facilitate file management and inspection within the agent's environment. These are used strictly for organizing data artifacts as part of the preparation workflow.
[DYNAMIC_EXECUTION]: Employs Python one-liners and heredoc scripts to perform runtime data validation, such as sniffing CSV delimiters and verifying the integrity of YAML ingestion contracts. These scripts are executed locally on the data being processed.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform untrusted data from various external formats (PDF, CSV, JSON, and API exports). This functionality creates an inherent surface for indirect prompt injection, where malicious instructions hidden within the source data could potentially influence the agent's behavior during the ingestion process.

sap-hana-data-prep