apple-mail
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
osascriptcommand 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.mdvia thecontent of msgAppleScript 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