skills/elizaos/eliza/apple-notes/Gen Agent Trust Hub

apple-notes

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies (LOW): The skill installs the 'memo' binary from a third-party Homebrew tap ('antoniorodr/memo/memo'). This source is not on the trusted organizations list. The severity is adjusted to LOW from MEDIUM as the dependency is essential for the skill's primary stated purpose.\n- Indirect Prompt Injection (LOW): The skill ingests untrusted data from Apple Notes, creating an attack surface.\n
  • Ingestion points: Note content retrieved via 'memo notes' and 'memo notes -s "query"'.\n
  • Boundary markers: Absent. No instructions or delimiters are provided to the agent to distinguish note content from system instructions.\n
  • Capability inventory: Execution of 'memo' CLI for creating, viewing, editing, and deleting notes.\n
  • Sanitization: Absent. Data from notes is processed directly by the agent.\n- Command Execution (SAFE): The skill executes the 'memo' CLI tool to interact with the local Apple Notes database on macOS, which matches the intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 06:11 PM