The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze existing project structures, source code, and configurations using tools like Read, Glob, and Grep to perform 'Context-Aware Generation'. This creates an attack surface where malicious instructions embedded in a user's project files could influence the agent's behavior during the generation process.
Ingestion points: Multiple modules (e.g., analytics-setup, cloudkit-sync, persistence-setup) indicate the skill reads existing Swift source files, entitlements, and project metadata to tailor generated code.
Boundary markers: The instructions do not specify the use of delimiters or markers to separate untrusted project data from the agent's system instructions during analysis.
Capability inventory: The skill possesses extensive capabilities, including the ability to Write and Edit project files and execute Bash commands, which increase the potential impact of an injection.
Sanitization: No sanitization or filtering logic for the ingested project content is described in the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill references several external dependencies from trusted organizations and well-known services for the generated projects.
Fetches the TelemetryDeck SwiftClient and Firebase iOS SDK from their official GitHub repositories for analytics integration.
References Sentry's official Cocoa SDK for error and crash monitoring.
Recommends the installation of industry-standard tools like fastlane and swiftlint via Homebrew for CI/CD workflows.
[COMMAND_EXECUTION]: The skill provides templates for automation and CI/CD scripts that involve command execution.
Generates GitHub Actions and Xcode Cloud scripts that use standard build tools like xcodebuild, simctl, agvtool, and security.
Includes a Swift automation script for screenshot generation that utilizes the Process API to execute shell commands for simulator management and build orchestration.
These scripts follow standard Apple development and automation patterns and are intended for execution by the developer or within a CI environment.

generators