The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the resend CLI tool to execute commands for listing and retrieving emails.
[EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of the @mjrussell/resend-cli package from the public npm registry.
[DATA_EXFILTRATION]: The skill accesses and displays potentially sensitive inbound email content, attachments, and domain configuration data.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by retrieving and processing the bodies of inbound emails from untrusted external senders. * Ingestion points: The resend email list and resend email get commands in SKILL.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. * Capability inventory: The agent can execute the resend CLI and jq commands. * Sanitization: No sanitization or filtering of the email data is performed before it enters the agent's context.

resend