apple-notes
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party CLI tool 'memo' from a personal GitHub repository via a Homebrew tap ('brew install antoniorodr/memo/memo'). This involves downloading and executing code from an unverified external source.
- [COMMAND_EXECUTION]: The skill uses the 'Bash' tool to run 'memo' commands, providing the agent with the ability to list, view, create, edit, and export data from the local macOS Notes application.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Apple Notes via 'memo view' and 'memo search' commands (ingestion points in SKILL.md). There are no boundary markers or sanitization procedures implemented to prevent the agent from following malicious instructions embedded in note content. The agent has 'Bash' and 'Write' capabilities (inventoried from SKILL.md), which could be leveraged if a processed note contains instructions to execute arbitrary shell commands or write malicious files to the workspace.
Audit Metadata