The Agent Skills Directory

[SAFE]: The skill's primary purpose is to perform automated cross-document consistency checks and game design analysis on project-local Markdown files.
[COMMAND_EXECUTION]: The skill uses Bash to execute git log --name-only, which is a standard operation for identifying modified files in a development workflow.
[EXTERNAL_DOWNLOADS]: No external downloads, package installations, or remote script executions were detected.
[DATA_EXFILTRATION]: There are no network operations or attempts to access sensitive system files (e.g., credentials, SSH keys). All file access is restricted to the game design project directory.
[PROMPT_INJECTION]: The instructions do not contain any attempts to override system prompts, bypass safety filters, or ignore previous instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GDD files. While it lacks explicit boundary markers for this data, its capabilities are limited and critical actions like writing reports or updating indexes are gated by the AskUserQuestion tool for user consent.
[SAFE]: The metadata and instructions are consistent with the stated purpose of game design review.

review-all-gdds