The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of @mjrussell/resend-cli via npm. This package is maintained by an individual developer and is not an official tool from Resend or the skill author, representing an unverifiable dependency from an unknown source.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from inbound emails.
Ingestion points: Email content and metadata retrieved via resend email list, resend email get, and resend email attachments as specified in SKILL.md.
Boundary markers: No delimiters or instructions to ignore embedded commands are included in the prompt instructions.
Capability inventory: The skill executes shell commands and uses jq to process data; malicious instructions in an email could attempt to influence these operations or the agent's next steps.
Sanitization: No sanitization or validation of the retrieved email content is performed before it is presented to the agent.
[COMMAND_EXECUTION]: The skill relies on executing shell commands for its core functionality, using the resend binary and the jq utility to list, fetch, and parse email data.

resend