The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to verify the configuration of the Resend API key and to send generated email sequences via network requests.
Evidence: Bash scripts are provided to source ~/.claude/.env.global and execute curl commands targeting https://api.resend.com/emails.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user requirements to generate email copy, which could be exploited for prompt injection in a downstream context.
Ingestion points: User-provided inputs regarding the sequence type, product/service, and target audience collected in the 'Gathering Requirements' section of SKILL.md.
Boundary markers: None are present to delimit user input from the rest of the generation instructions.
Capability inventory: The skill has network access through the Bash tool to interact with the Resend API.
Sanitization: There is no evidence of sanitization or escaping of user-provided inputs.

email-sequence