The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill is configured to download and execute the resend-mcp package from the npm registry using npx -y at runtime as defined in the mcp frontmatter section.
[COMMAND_EXECUTION]: The skill uses the npx command to spawn the Resend MCP server, which manages the communication between the agent and the Resend API.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could be manipulated to influence the agent's behavior.
Ingestion points: The send_email and batch_send_emails operations ingest user-provided strings for the email subject and body (HTML or plain text) as described in SKILL.md.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the email content are provided.
Capability inventory: The skill has network capabilities (sending emails via the Resend API) and potential local file system access (reading files via the path field in attachments).
Sanitization: The instructions do not specify any sanitization or validation logic for the content processed by the email tools.

resend