notes-organize

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local script located at $HOME/.claude/plugins/marketplaces/cc-skills/plugins/notes-commander/scripts/notes.ts using the bun runtime. This is the intended execution model for this utility.
  • [PROMPT_INJECTION]: The skill processes user-controlled data (note titles and folder names), which constitutes a surface for indirect prompt injection.
  • Ingestion points: Note titles, folder names, and account names are retrieved from the macOS Notes application and processed by the agent to determine organization logic.
  • Boundary markers: The instructions do not specify any explicit boundary markers or delimiters for note metadata, though they advise using unique IDs to resolve ambiguity.
  • Capability inventory: The skill possesses the capability to execute shell commands (via bun) and interact with the macOS Notes database via AppleScript.
  • Sanitization: The markdown documentation does not explicitly detail sanitization procedures for special characters in titles, though the underlying TypeScript logic in notes.ts is intended to handle these primitives.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:24 AM
Security Audit — agent-trust-hub — notes-organize