The Agent Skills Directory

[SAFE]: The skill provides instructions for frontend design system management. All operations are restricted to reasoning and documentation within the agent's context. No malicious patterns, obfuscation, or dangerous command executions were detected.- [INDIRECT_PROMPT_INJECTION]: Potential attack surface identified through the ingestion of untrusted UI requirements. 1. Ingestion points: UI requirements and component inventory (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Reasoning and Markdown generation (SKILL.md). 4. Sanitization: Absent. The risk is assessed as safe because the skill does not have access to tools that modify the file system, perform network operations, or execute code.

design-system