apple-books-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the apple-books-mcp package from an external third-party repository via the uvx tool.
  • [COMMAND_EXECUTION]: The user is instructed to run shell commands using npx and uvx to set up the MCP server environment.
  • [REMOTE_CODE_EXECUTION]: The skill relies on external code provided by the apple-books-mcp package, which executes locally to retrieve data from the Apple Books application.
  • [PROMPT_INJECTION]: The skill processes user-generated content from book highlights and notes, providing an entry point for indirect prompt injection.
  • Ingestion points: Highlighted text and annotations retrieved from the Apple Books library.
  • Boundary markers: The prompt lacks specific delimiters to separate user data from agent instructions.
  • Capability inventory: Includes file reading through the MCP server and markdown file creation via Python scripts.
  • Sanitization: No sanitization is performed on the extracted highlight text before it is used in markdown templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 09:20 AM