The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill. The content consists entirely of instructional markdown and evaluation JSON for UI design principles.
[NO_CODE]: The skill does not contain any executable scripts, shell commands, or external package dependencies. It operates entirely as a set of logical instructions for the AI agent.
[METADATA_POISONING]: Metadata fields such as name, description, and subject are consistent with the skill's stated purpose and contain no deceptive instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill defines how to process design requirements (which could be user-provided), it lacks dangerous capabilities such as file-writing, network operations, or shell execution that could be exploited via indirect injection.

layout-composition