The Agent Skills Directory

[SAFE]: The skill's primary functionality is to analyze local game data and design documents to identify balance issues. It uses standard file-system tools (Read, Glob, Grep, Write) and does not request network access or execute remote scripts.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a standard indirect prompt injection surface as it ingests untrusted data from project files.
Ingestion points: Processes ScriptableObjects and data assets from Assets/Game/Data/ and design documents from design/gdd/ as defined in references/claude-skill.md (Phases 2 and 3).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the game data or design files.
Capability inventory: The skill is permitted to use the Write tool to save reports to the design/balance/ directory.
Sanitization: No explicit sanitization or schema validation of the content within the analyzed files is performed prior to processing.
Contextual Note: This risk is considered negligible as the skill lacks network capabilities and its operations are restricted to the local project environment.

balance-check