The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and run the @useclawlink/cli package from the official NPM registry. This package is an official tool provided by the vendor 'clawlink-hq'.
[COMMAND_EXECUTION]: The skill uses shell commands via the ClawLink CLI to perform actions such as logging in, connecting to New Relic, and executing API calls. These commands are necessary for the skill's primary function.
[CREDENTIALS_UNSAFE]: The skill documentation mentions that session credentials are stored locally at ~/.clawlink/credentials.json. This is standard behavior for CLI tools that maintain authenticated sessions across executions.
[PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it processes natural language descriptions to find and execute actions. However, the instructions explicitly direct the agent to 'confirm with the user before any write', which acts as a security boundary for high-stakes operations.

new-relic