The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The README.md file contains instructions to download and install a zip package from an external GitHub repository (https://github.com/patrickfreyer/apple-mail-mcp/releases). This represents an external dependency reference not directly hosted by the stated author.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process untrusted external data from emails, which can be used to influence the agent's behavior.
Ingestion points: Functions like get_email_with_content and search_emails in SKILL.md bring external email bodies into the conversation context.
Boundary markers: There are no explicit instructions in SKILL.md to treat the content of fetched emails purely as data or to ignore any instructions found within them.
Capability inventory: The skill includes instructions for powerful operations such as forward_email, reply_to_email, manage_trash, and export_emails, which could be abused if the agent follows malicious instructions contained in a processed email.
Sanitization: No sanitization or validation logic is defined to mitigate the risk of instructions embedded in email content.

email-management-expert