The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown focused on frontend aesthetics and design principles. No scripts, binaries, or command executions were identified within the skill content.\n- [INDIRECT_PROMPT_INJECTION]: The skill implements a context-gathering protocol that instructs the agent to read from a project-specific file (.impeccable.md). While this represents a data ingestion surface, it is a standard configuration pattern for providing design requirements and carries minimal risk given the skill's restricted capabilities.\n
Ingestion points: The agent is directed to read .impeccable.md from the project root if project context is not already present in the prompt (SKILL.md).\n
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified for the context file ingestion.\n
Capability inventory: The skill does not request or utilize tools for network access, arbitrary command execution, or file writing.\n
Sanitization: No input validation or content sanitization is described for the ingested design context data.

impeccable-design