The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx starkfi@latest to perform DeFi operations, which results in the dynamic download and execution of the starkfi package from the npm registry whenever the skill is used.
[REMOTE_CODE_EXECUTION]: Executing unversioned remote code via npx @latest introduces a supply chain risk, as any compromise of the starkfi package or its dependencies could lead to the execution of malicious code on the host system.
[COMMAND_EXECUTION]: The allowed-tools configurations utilize shell wildcards (e.g., npx starkfi@latest batch *), allowing arbitrary user-supplied input to be passed directly to the shell. This pattern creates a surface for command injection if the agent does not strictly sanitize or validate user inputs before command assembly.

batch