The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx @useclawlink/cli to download and execute the ClawLink command-line interface from the NPM registry. This is a standard delivery mechanism for the vendor's provided tooling.
[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands via the npx utility to manage authentication and execute service actions such as login, connect, and run.
[PROMPT_INJECTION]: The skill ingests untrusted data from an external source (emails) through actions such as agent_mail_get_message. This creates an indirect prompt injection surface where malicious email content could attempt to influence the agent's actions.
Ingestion points: SKILL.md (via agent_mail_get_message and agent_mail_list_messages actions).
Boundary markers: None specified in the instructions for isolating external email content.
Capability inventory: SKILL.md (shell command execution via npx, email sending via agent_mail_send_email).
Sanitization: None mentioned in the skill instructions.

agent-mail