The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli Node.js package globally. This package is the official command-line interface for the Membrane platform, which is the author of this skill.
[COMMAND_EXECUTION]: The integration relies on executing shell commands using the membrane CLI tool. These commands are used to log in, search for connectors, and run specific Zoho Mail actions like sending or reading emails.
[PROMPT_INJECTION]: The skill includes functionality to retrieve email content via the get-email-content action. This represents a potential surface for indirect prompt injection, where malicious instructions inside an email could attempt to influence the agent's behavior. However, this is a known risk factor for any email-handling skill and is managed by the agent's underlying safety filters.
Ingestion points: The get-email-content and list-emails actions in SKILL.md bring external email data into the agent's context.
Boundary markers: Not explicitly defined in the prompt instructions.
Capability inventory: The skill has the capability to send emails (send-email) and make arbitrary API requests via membrane request.
Sanitization: No specific sanitization logic is detailed in the skill instructions.

zoho-mail