The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform a shell command (ls) to verify the existence of a design kit. The command checks for a directory at ${CLAUDE_SKILL_DIR}/../../../tokens to confirm the environment is correctly initialized before proceeding.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple external local files, which serves as an attack surface for indirect prompt injection if those files contain untrusted content.
Ingestion points: Reads content from workflows/prototyping.md, tokens/*, components/*, taste/*, and accessibility/* located three levels above the skill directory.
Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent when processing the content of these files.
Capability inventory: The skill uses file system access (read/ls) to retrieve design guidelines and tokens to generate UI artifacts and validation plans.
Sanitization: There is no evidence of sanitization or validation of the content ingested from the design kit files.

prototype