The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requests access to the Bash tool to perform development tasks, manage sprint statuses, and execute testing frameworks within the local environment.\n- [EXTERNAL_DOWNLOADS]: Installation instructions reference the npx package runner and an external GitHub repository (supercent-io/skills-template) for project scaffolding.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and documenting external project data.\n
Ingestion points: Reads game project files and documentation using Read, Grep, and Glob tools across multiple workflow phases.\n
Boundary markers: No explicit delimiters or 'ignore' instructions are provided to separate project data from agent commands.\n
Capability inventory: Agents possess significant capabilities including Write (file system modification) and Bash (shell execution) which could be leveraged if malicious instructions are encountered in project files.\n
Sanitization: No evidence of sanitization or validation for external project content is present in the skill configuration.

bmad-gds