The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes the @useclawlink/cli package from the public NPM registry using npx. This is the primary method for interacting with the service.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage authentication and Freshdesk data. It notes that credentials for the service are stored locally at ~/.clawlink/credentials.json after the login process.
[REMOTE_CODE_EXECUTION]: The use of npx to run a remote package from NPM constitutes a form of remote code execution. This behavior is documented as a core part of the skill's setup and operation using the vendor's official CLI tool.
[PROMPT_INJECTION]: The skill acts as a bridge for processing external data from Freshdesk, including ticket notes and contact information. This creates an indirect prompt injection surface where instructions embedded in support tickets or customer data could potentially influence the agent's behavior.
Ingestion points: Freshdesk ticket content, notes, contacts, and company data.
Boundary markers: None explicitly defined in the provided instructions.
Capability inventory: Subprocess execution via npx @useclawlink/cli for reading and writing data.
Sanitization: Not specified; the skill relies on the agent's internal safety filters.

freshdesk