The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx @useclawlink/cli to fetch and execute the integration tool directly from the npm registry. This is the primary mechanism for accessing the vendor's service.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to log in, connect accounts, and run specific marketing actions. These commands are necessary for the skill's functionality and are restricted to the vendor-provided CLI.
[CREDENTIALS_UNSAFE]: The documentation notes that credentials resulting from the login process are stored locally at ~/.clawlink/credentials.json. This is standard behavior for a command-line tool to manage session persistence.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading data from external Toneden marketing feeds, which creates a potential surface for indirect instructions to enter the agent's context.
Ingestion points: Data retrieved via npx @useclawlink/cli run toneden or actions commands.
Boundary markers: Not explicitly defined in the provided markdown.
Capability inventory: Execution of shell commands via the ClawLink CLI.
Sanitization: Standard CLI output processing is expected; no custom sanitization logic is specified in the instructions.

toneden