The Agent Skills Directory

[SAFE]: The skill is primarily instructional, offering architectural patterns and troubleshooting documentation for Apple's game frameworks (SpriteKit, SceneKit, RealityKit, and GameController).
[INDIRECT_PROMPT_INJECTION]: The skill includes an automated auditor (spritekit-auditor.md) designed to scan and analyze external source code files. This establishes an ingestion surface for untrusted data.
Ingestion points: The auditor uses the Glob and Read tools to ingest and analyze **/*.swift files from the project environment.
Boundary markers: The instructions do not define specific delimiters or warnings to separate the analyzed code from the agent's internal reasoning.
Capability inventory: The auditor is restricted to static analysis using Glob, Grep, and Read tools; it lacks capabilities for arbitrary command execution, network access, or file modification during the audit process.
Sanitization: The skill performs read-only analysis of source code and does not include mechanisms to validate or sanitize the content of the files being audited.

axiom-games