The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements a mandatory enforcement mechanism that requires the agent to read external files (design-system.md) and project source code to determine UI constraints. This creates a surface for indirect prompt injection where instructions embedded in project data could influence agent behavior.
Ingestion points: The agent reads user-generated configuration files (design-system.md) and project source files (*.tsx, *.jsx) using the Read and Grep tools.
Boundary markers: There are no specified delimiters or "ignore embedded instructions" warnings when the agent ingests the design system guidelines or source code.
Capability inventory: The skill possesses the Bash, Write, and Edit tools, allowing it to execute scripts and modify project files.
Sanitization: No sanitization or validation logic is present to filter out potential instructions or malicious patterns within the project files being processed.
[COMMAND_EXECUTION]: The skill utilizes local shell scripts (setup-design-system.sh, validate-design-system.sh) to automate the creation of design guidelines and perform compliance checks on the codebase. These scripts use standard system utilities like sed, find, and grep to perform pattern matching and file manipulation within the project directory.

design-system-enforcement