The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The setup.sh script installs required Node.js dependencies from the official NPM registry. This is a standard and safe operation for setting up the skill's dependencies.
[COMMAND_EXECUTION]: The skill uses JavaScript and Bash scripts to perform its intended email and configuration tasks. All command execution is scoped to the skill's primary functionality and does not involve unauthorized privilege escalation.
[CREDENTIALS_UNSAFE]: The skill handles sensitive email credentials by storing them in a local .env file. It follows secure practices by setting the file permissions to 600 (owner read/write only) and advising users to use App Passwords or authorization codes instead of primary account passwords.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from email bodies and attachments.
Ingestion points: External data enters through email fetching functions in scripts/imap.js.
Boundary markers: Explicit boundary markers are not defined in the skill instructions.
Capability inventory: The skill can send network data via scripts/smtp.js and write files via scripts/imap.js.
Sanitization: Implements filename sanitization to prevent path traversal and uses strict directory whitelists (ALLOWED_READ_DIRS, ALLOWED_WRITE_DIRS) to control file system access.

imap-smtp-email