The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and parse external 'DESIGN.md' files from a community-maintained catalog (getdesign.md). Because these files are community-contributed, they could contain malicious instructions designed to hijack the agent's behavior when it parses the visual rules.
Ingestion points: The brand_fetch_design_md tool and associated workflow in SKILL.md fetch external markdown content into the agent's context.
Boundary markers: Absent. There are no instructions provided to treat the fetched content as untrusted or to ignore embedded natural language instructions within the design specs.
Capability inventory: The skill possesses significant capabilities, including generating full HTML scaffolds (generate_template), writing project configuration files (scripts/apply_ui_rules.py), and exporting full project scaffolds (export_project).
Sanitization: Absent. The skill logic does not include validation or sanitization of the fetched markdown content before it is used to override design tokens and system behavior.
[EXTERNAL_DOWNLOADS]: The documentation encourages the use of npx getdesign@latest, which involves downloading and executing a third-party package from a public registry. While the service is described as popular, executing unversioned remote code via npx carries inherent supply chain risks.

ui-designer