skills/steipete/clawdis/apple-notes/Gen Agent Trust Hub

apple-notes

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill installs the memo binary via a custom Homebrew tap (antoniorodr/memo/memo) and suggests manual installation via pip. These sources are not within the trusted organization list, posing a supply-chain risk.
  • [COMMAND_EXECUTION] (LOW): The skill's primary operation involves executing the memo command with various arguments to interact with the system's Apple Notes database.
  • [DATA_EXPOSURE] (LOW): The skill is designed to read, search, and export Apple Notes. While this is the intended purpose, it grants the agent access to potentially sensitive personal information stored in the Notes app.
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection risk exists. If the agent reads a note (via memo notes or memo notes -s) that contains malicious instructions, those instructions could influence the agent's subsequent behavior.
  • Ingestion points: Output of memo notes (listing/viewing note content).
  • Boundary markers: None specified in the provided markdown.
  • Capability inventory: Execution of shell commands (memo), file export.
  • Sanitization: None detected in the skill definition.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:07 PM