apple-notes
Warn
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
memoutility from a third-party Homebrew tap located atantoniorodr/memo, which is not an officially verified or trusted service provider. - [COMMAND_EXECUTION]: The skill executes shell commands using the
memoCLI to perform operations such as creating, searching, and exporting system notes on macOS. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because the agent reads and processes user-generated text from Apple Notes.
- Ingestion points: Untrusted content is ingested when the agent lists notes (
memo notes), searches them (memo notes -s), or views them for editing. - Boundary markers: Absent. The skill instructions do not provide delimiters or security framing to prevent the agent from obeying instructions embedded within the note text.
- Capability inventory: The agent has access to shell command execution (
memo), file system export capabilities, and interactive note modification. - Sanitization: Absent. Content retrieved from the Notes application is processed without validation or filtering.
Audit Metadata