The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes curl to interact with the Resend REST API endpoints for operations like sending emails and managing resources.
[DATA_EXFILTRATION]: Performs network requests to api.resend.com to deliver emails and manage service resources. This targets a well-known email service provider and is an intended function of the skill.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted user input into email payloads.
Ingestion points: User-provided values for email fields including 'to', 'subject', 'html', and 'text' in SKILL.md.
Boundary markers: Delimiters or instructional guards to separate untrusted user content from the request structure are absent.
Capability inventory: The skill has the capability to trigger outbound emails and modify API resources via curl as defined in SKILL.md.
Sanitization: There is no evidence of input validation, escaping, or filtering for the data interpolated into the API requests.

resend