The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing Apple Notes content, creating a surface for indirect prompt injection. 1. Ingestion points: Note bodies are accessed via the n.plaintext() method in the JXA script within SKILL.md. 2. Boundary markers: The skill instructs to reject network-provided note content but does not specify delimiters for exported data. 3. Capability inventory: The skill utilizes osascript (AppleScript/JXA), bash, and security tools for system interaction. 4. Sanitization: Recommends skipping locked notes and redacting failures.- [COMMAND_EXECUTION]: The skill demonstrates the use of osascript and security CLI tools to automate macOS features. These tools are listed in the allowed-tools frontmatter and the usage patterns follow industry-standard security best practices, such as using umask 077 and trap for cleanup.- [DYNAMIC_EXECUTION]: The skill uses osascript -e to execute JavaScript for Automation (JXA) code defined within a shell script. This dynamic execution is local, non-obfuscated, and serves the primary purpose of structured data export.

apple-notes-security-basics