The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from Microsoft Excel workbooks which could contain adversarial instructions.
Ingestion points: Data is retrieved from workbooks via the @useclawlink/cli tool during execution of Excel actions.
Boundary markers: The skill instructions explicitly direct the agent to 'confirm with the user before any write,' serving as a human-in-the-loop safety measure.
Capability inventory: The agent can perform a variety of actions including adding charts, tables, and worksheets, and modifying workbook permissions using shell commands.
Sanitization: No specific content sanitization or structured boundary markers for cell data are defined.
[COMMAND_EXECUTION]: The skill utilizes the @useclawlink/cli package to perform actions. These commands are part of the core functionality provided by the vendor to facilitate the Microsoft Excel integration.

microsoft-excel