apple-notes

Warn

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the memo CLI tool from a third-party Homebrew tap (antoniorodr/memo). This introduces an external dependency from a source that is not verified or explicitly trusted.
  • Evidence: brew tap antoniorodr/memo && brew install antoniorodr/memo/memo in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes user notes from Apple Notes. If these notes contain data from untrusted sources (such as web clippings or shared content), they could include malicious instructions that the agent might inadvertently execute.
  • Ingestion points: The agent retrieves note content using memo notes and memo notes -s "query" (SKILL.md).
  • Boundary markers: The skill lacks instructions or delimiters to isolate note content from the agent's system prompt or to explicitly ignore embedded instructions.
  • Capability inventory: The skill provides capabilities to create, edit, move, and delete notes via the memo CLI (SKILL.md).
  • Sanitization: There is no indication of validation or sanitization of the content retrieved from the Apple Notes database.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 1, 2026, 05:58 AM