The Agent Skills Directory

[SAFE]: Analysis of the skill instructions and reference materials revealed no evidence of malicious intent, obfuscation, or unauthorized data access.
[COMMAND_EXECUTION]: The skill requests access to Bash and Write tools to automate game development workflows, including the generation of design artifacts, project scaffolding, and test execution. These operations are consistent with the skill's primary purpose.
[EXTERNAL_DOWNLOADS]: The installation instructions and documentation reference external GitHub repositories (supercent-io and bmad-code-org) for the skill template and upstream module code. These sources are associated with the skill's development and are documented neutrally.
[PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill processes project files and code.
Ingestion points: Files are analyzed via bmad-gds-document-project, bmad-gds-code-review, and playtesting commands.
Boundary markers: The provided documentation does not define specific delimiters or instructions to ignore embedded commands in analyzed data.
Capability inventory: The skill uses Bash, Write, and Read across multiple agents.
Sanitization: No explicit sanitization or filtering of project content is mentioned in the skill definition.

bmad-gds