The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions and documentation recommend installing or updating the official @uipath/cli package via npm to ensure the rules engine commands are available.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run various uip rules subcommands (init, refresh, validate, debug, list, get, describe) which are necessary for the creation, testing, and deployment of business rules logic.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it ingests and processes external data such as DMN files, spreadsheets, and natural language policies to generate decision tables.
Ingestion points: Data enters the agent context through the reading of .dmn, project.uiproj, and entry-points.json files, as well as user-provided spreadsheets or policy descriptions.
Boundary markers: The instructions recommend displaying the logic as a markdown table for human review before final authoring, providing a manual verification step.
Capability inventory: The skill has access to the Bash tool for CLI execution and Write/Edit tools for modifying project files.
Sanitization: No automated sanitization of external content is specified before interpolation into the decision logic.

uipath-rules