The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the npx @useclawlink/cli tool to interact with the Splitwise service, including authentication and data management.
[EXTERNAL_DOWNLOADS]: The skill relies on npx to download and execute the @useclawlink/cli package from the NPM registry. This package is required for the integration to function.
[PROMPT_INJECTION]: There is an indirect prompt injection surface as the agent processes data (such as transaction details or group names) retrieved from the external Splitwise API.
Ingestion points: Data from Splitwise enters the agent's context through the output of CLI commands like npx @useclawlink/cli actions and npx @useclawlink/cli run.
Boundary markers: The instructions do not provide specific boundary markers or delimiters to isolate untrusted data retrieved from the API from the agent's system instructions.
Capability inventory: The skill allows the agent to execute shell commands and perform read/write operations on financial data in Splitwise.
Sanitization: The skill documentation does not describe any validation or sanitization processes for the data fetched from the Splitwise service before it is presented to the agent.

splitwise