The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various operations using the @useclawlink/cli, including authentication (login), service connection (connect), and financial operations (run, actions, describe). These commands interact with the local shell to manage FreeAgent data.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx @useclawlink/cli to download and run the ClawLink command-line interface directly from the npm registry. This tool is the primary interface for all FreeAgent operations.
[INDIRECT_PROMPT_INJECTION]: The skill accesses external financial data from FreeAgent, such as company details, accounting transactions, and profit/loss summaries. This data is ingested into the agent's context, creating a potential surface for indirect prompt injection if the external records contain malicious instructions.
Ingestion points: Data retrieved from FreeAgent via npx @useclawlink/cli run/actions is processed by the agent.
Boundary markers: The skill suggests reading data first and confirming with the user before performing any write operations, which provides a manual checkpoint.
Capability inventory: The agent has the capability to execute shell commands and modify financial records in FreeAgent.
Sanitization: There are no explicit sanitization or filtering instructions provided for the data returned by the CLI tool.

freeagent