apple-notes

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installing the memo tool via a third-party Homebrew tap antoniorodr/memo. This introduces a dependency on code maintained by an individual user outside of the primary vendor or trusted organizations.\n- [COMMAND_EXECUTION]: The skill uses the memo CLI to interact with the local macOS system. It also relies on the user's $EDITOR environment variable to launch a text editor for note creation, which involves spawning subprocesses.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes content from Apple Notes, which is external, user-controlled data that could contain malicious instructions.\n
  • Ingestion points: Data retrieved via memo notes list and search commands as described in SKILL.md.\n
  • Boundary markers: Absent; the instructions do not specify any delimiters or warnings to ignore instructions found within note data.\n
  • Capability inventory: Local command execution via the memo CLI for creating, editing, and deleting notes.\n
  • Sanitization: The skill does not implement or suggest any sanitization of the note content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 06:32 PM