The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructs the agent to read .agents/product-marketing-context.md or .claude/product-marketing-context.md if they exist. This is a legitimate file access request intended to provide the agent with necessary context about the user's product or service to better perform the email sequence design task.
[PROMPT_INJECTION]: There is a minimal risk of indirect prompt injection as the skill processes external data from a product marketing context file. If that file were to contain adversarial instructions, they could influence the agent's behavior. However, the skill does not grant the agent capabilities to perform dangerous actions based on that data (e.g., no network operations or command execution are triggered by the ingested data).
[SAFE]: All tool integrations mentioned (Customer.io, Mailchimp, Resend, etc.) are well-known, legitimate services in the email marketing industry. The skill provides links to internal documentation and does not contain any hardcoded credentials or unauthorized remote downloads.

email-sequence