skills/gquthier/clawg/apple-notes/Gen Agent Trust Hub

apple-notes

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the memo utility from a personal GitHub repository (antoniorodr/memo) using the Homebrew package manager. This creates a dependency on third-party code that is not maintained by a verified organization or well-known service provider.\n- [COMMAND_EXECUTION]: The skill executes the memo command-line tool to perform actions such as listing, searching, creating, and deleting notes, which involves interaction with local macOS system databases and the Apple Notes application.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from Apple Notes through the memo notes command. If a user's note contains malicious instructions, the agent might inadvertently follow them during processing or summarization tasks.\n
  • Ingestion points: Reads content from the local Apple Notes database via memo notes.\n
  • Boundary markers: No delimiters or instructions are provided to distinguish note data from system instructions.\n
  • Capability inventory: Uses the memo binary for note management operations including deletion and export.\n
  • Sanitization: Content retrieved from notes is processed without sanitization or validation to detect embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 03:12 PM