apple-notes
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external CLI tool ('memo') from a third-party Homebrew repository (
antoniorodr/memo/memo) as specified in theSKILL.mdfrontmatter and setup instructions. - [COMMAND_EXECUTION]: The skill's primary functionality is built upon executing the
memocommand-line utility to perform system-level operations, including searching, creating, and modifying Apple Notes on macOS. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it retrieves and processes content from Apple Notes, which may contain untrusted data.
- Ingestion points: Untrusted data enters the agent context via the
memo notesandmemo notes -scommands described inSKILL.md. - Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands within the notes.
- Capability inventory: The skill permits data modification through note creation (
-a), editing (-e), and deletion (-d) as documented inSKILL.md. - Sanitization: Absent; the instructions do not provide methods for validating or escaping note content before the agent processes it.
Audit Metadata