skills/simota/agent-skills/atelier/Gen Agent Trust Hub

atelier

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as a pipeline orchestrator that processes external, potentially untrusted data to drive the actions of downstream agents.
  • Ingestion points: The skill ingests aesthetic direction from external files like direction.md (via the Vision agent), user-provided briefs, and design data extracted from Figma files via the Frame delegate.
  • Boundary markers: It utilizes the DESIGN_INTENT_HANDOFF structured schema to define instruction boundaries and standardized metadata when delegating tasks to other agents.
  • Capability inventory: The skill orchestrates high-privilege agents including Artisan (responsible for production frontend implementation) and Forge (responsible for rapid prototyping). It also performs file system operations within the .agents/ directory to maintain a persistent design system.
  • Sanitization: It employs structured handoff bundles and specific operation layers (such as parametric sliders and structured comments) to communicate intent, which provides more structure than free-form natural language prompts.
  • [EXTERNAL_DOWNLOADS]: The skill references official resources from a well-known technology provider.
  • Evidence: Includes links to Anthropic's official newsroom (e.g., https://www.anthropic.com/news/claude-design-anthropic-labs) to provide context for its design workflow philosophy.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:03 PM