The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the @useclawlink/cli tool to perform actions in Zendesk. It instructs the agent to run commands such as npx @useclawlink/cli actions zendesk and npx @useclawlink/cli run zendesk to read and modify tickets and users.
[EXTERNAL_DOWNLOADS]: The instructions rely on npx @useclawlink/cli, which downloads the latest version of the CLI tool from the NPM registry at runtime.
[CREDENTIALS_UNSAFE]: The skill documents that the login process stores a minted key in the user's home directory at ~/.clawlink/credentials.json. This is standard behavior for the vendor's CLI tool and does not involve hardcoded secrets within the skill itself.
[PROMPT_INJECTION]: The skill processes external data from Zendesk (tickets, users, organizations), which constitutes an indirect prompt injection surface.
Ingestion points: Data retrieved from Zendesk ticket descriptions, user names, and custom objects via CLI output.
Boundary markers: None explicitly defined in the provided CLI command examples.
Capability inventory: The skill can perform network operations and file writes through the vendor CLI.
Sanitization: Not specified; the skill relies on the agent's default handling of tool output and user confirmation before write actions.

zendesk