apple-notes

Warn

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the memo CLI tool from a third-party Homebrew tap (antoniorodr/memo). This repository is not from a trusted organization or well-known service.\n- [COMMAND_EXECUTION]: The skill executes multiple shell commands using the memo binary to list, search, add, and delete notes within the macOS environment. This involves direct interaction with the system's underlying Notes.app via a CLI interface.\n- [PROMPT_INJECTION]: This skill is vulnerable to indirect prompt injection because it reads content from local Apple Notes. If a note contains malicious instructions (e.g., from a shared note or external sync), the agent may inadvertently follow them while processing the note's text.\n
  • Ingestion points: Reading note titles and body content via memo notes, including search results.\n
  • Boundary markers: There are no defined delimiters or instructions to treat note content as untrusted data.\n
  • Capability inventory: The skill can execute local commands and perform write/delete operations on the notes database.\n
  • Sanitization: The skill does not implement any visible sanitization or filtering of the text retrieved from notes before it enters the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:13 AM