The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of analyzing and documenting existing projects and executing developer stories based on project content.
Ingestion points: The bmad-gds-document-project and bmad-gds-dev-story commands read and process external project files (source code and documentation) into the agent context.
Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions embedded within the processed project files.
Capability inventory: The skill utilizes Bash, Read, Write, Grep, and Glob tools, providing a broad surface for potential command execution or file modification if an injection occurs.
Sanitization: No sanitization or validation of the ingested file content is specified in the instruction set.
[COMMAND_EXECUTION]: The skill uses the Bash tool to implement development tasks, manage sprint status, and execute test frameworks. This is standard behavior for a development-focused agent skill.
[DATA_EXFILTRATION]: The skill utilizes Read and Write tools to interact with project artifacts such as Game Design Documents (GDD), technical architecture files, and source code. Access is restricted to the tools allowed in the skill configuration.

bmad-gds