apple-mail

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the osascript command to execute AppleScript for automating the Apple Mail application. This is a standard and documented method for interacting with macOS system applications.
  • [DATA_EXPOSURE]: The skill accesses local email data, including sender information, subjects, and message content. This data access is localized to the user's machine and is required for the skill's stated functionality.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted external data (email bodies).
  • Ingestion points: Email content is retrieved in SKILL.md via the content of msg AppleScript property.
  • Boundary markers: There are no explicit delimiters or boundary markers used in the snippets to separate retrieved content from agent instructions.
  • Capability inventory: The skill can read, search, and create drafts in Apple Mail using osascript; it does not have arbitrary shell or network write permissions.
  • Sanitization: The scripts do not perform explicit sanitization of the email content before returning it to the agent environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM