The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a shell command to execute a Ruby script for Xcode project integration.
Evidence: ruby ${CLAUDE_PLUGIN_ROOT}/skills/add-to-xcode/scripts/add_to_xcode.rb <filepath>
This is a standard workflow for maintaining project parity in iOS development environments and utilizes an internal environment variable to reference a sibling skill.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external Android source code, which constitutes a potential attack surface for indirect prompt injection if the source code contains malicious instructions.
Ingestion points: Android codebase files provided by the user (e.g., Kotlin files, XML resources).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts in the source files.
Capability inventory: The agent has the capability to read files from a user-specified directory, create new .swift files in the current workspace, and execute a local Ruby script.
Sanitization: No explicit sanitization or filtering of the ingested source code is performed before processing.
As this analysis of source code is the primary intended function of the skill, the risk is inherent to the use case.

android-to-ios