apple-notes
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill performs its stated function of reading Apple Notes using standard macOS system tools.
- [COMMAND_EXECUTION]: The skill uses osascript to execute AppleScript commands for interacting with the macOS Notes application. This is the intended and standard mechanism for the skill's purpose.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted content from the user's Apple Notes.
- Ingestion points: Note content is retrieved and displayed by scripts/read-note.sh and scripts/search-notes.sh.
- Boundary markers: None present to isolate note content.
- Capability inventory: The skill is limited to read-only operations via AppleScript; it lacks network access or write permissions.
- Sanitization: No sanitization or escaping is performed on the retrieved note data before it is presented to the agent.
Audit Metadata