The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the @useclawlink/cli command-line tool to perform actions in Resend. This is a vendor-owned utility intended for the skill's primary functionality.
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to run the @useclawlink/cli package using npx, which downloads it from the official NPM registry. The package belongs to the vendor (clawlink-hq).
[PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it retrieves data from external sources (Resend emails, audiences, and contacts) that could contain malicious instructions designed to manipulate the agent.
Ingestion points: Data returned to the agent by actions like resend_get_email, resend_list_contacts, and other 'get' or 'list' functions.
Boundary markers: The skill does not specify the use of delimiters or 'ignore embedded instructions' warnings when processing fetched data.
Capability inventory: The agent possesses write capabilities such as resend_send_email, resend_create_contact, and resend_delete_contact which could be abused if an injection is successful.
Sanitization: No explicit sanitization or filtering of the content retrieved from the Resend API is described in the skill's instructions.

resend