The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to manage the environment for its reporting.
Evidence: Executes mkdir -p .design/system to prepare the output directory for generated documentation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of scanning untrusted workspace data.
Ingestion points: Reads local workspace files including package.json, component source code, CSS files, and various configuration files (tsconfig.json, tailwind.config.*).
Boundary markers: None identified. The skill does not use specific delimiters or instructions to ignore embedded prompts within the files it reads.
Capability inventory: The skill has the ability to Write to the file system and execute Bash commands.
Sanitization: No explicit sanitization or validation of the content read from workspace files is performed before processing.

design-system