The Agent Skills Directory

[SAFE]: The skill follows its stated purpose without incorporating malicious logic, obfuscation, or unauthorized credential access.
[EXTERNAL_DOWNLOADS]: The skill utilizes WebSearch and WebFetch to identify the latest stable versions of game engines and to retrieve technical documentation. This is an intended functional requirement for maintaining up-to-date environment configurations.
[DATA_EXPOSURE]: The skill reads project configuration files, specifically CLAUDE.md and game-concept.md, to determine the appropriate engine and versioning required for the user's project.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests untrusted data from the web (such as third-party migration guides) and stores it in the project's documentation files, which are later imported into the agent's context.
Ingestion points: WebFetch operations described in Step 7 of SKILL.md for migration and upgrade guides.
Boundary markers: Absent; the fetched content is written to markdown files without specific isolation markers or instructions to ignore embedded commands.
Capability inventory: The skill uses Write, Edit, WebSearch, and WebFetch tools.
Sanitization: No explicit sanitization or validation of the fetched remote content is performed before it is written to the local filesystem.

setup-engine