skills/openclaw/skills/design-style/Gen Agent Trust Hub

design-style

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external assets from well-known sources to implement specific design aesthetics.
  • Multiple prompt files (e.g., prompts/Industrial.md, prompts/Neo-brutalism.md) reference Google Fonts for typography.
  • prompts/Industrial.md and prompts/Web3.md reference transparenttextures.com for UI pattern assets.
  • [COMMAND_EXECUTION]: The skill includes shell scripts for diagnostic and administrative purposes.
  • scripts/list-styles.sh: Lists available design style files in the prompts directory.
  • scripts/verify-skill.sh: Validates the skill's file structure and configuration.
  • [PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data during code generation.
  • Ingestion points: Processes user requests for UI components and design preferences as described in SKILL.md and reference.md.
  • Boundary markers: Lacks explicit delimiters or "ignore embedded instructions" warnings when interpolating user requirements into generated implementation plans.
  • Capability inventory: Uses Read, Glob, and Grep tools to retrieve design system documentation.
  • Sanitization: No explicit input sanitization or validation of user-provided design descriptions is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 04:58 PM