atomic-design
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided UI requirements and design tokens. 1. Ingestion points: User queries relating to UI components and design hierarchies (SKILL.md). 2. Boundary markers: None present. 3. Capability inventory: The skill contains no executable code, network operations, or file-writing capabilities. 4. Sanitization: None present. Because the skill lacks sensitive capabilities, this ingestion surface is considered safe.
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to download a related 'tdd' skill from the author's repository (jwilger/agent-skills) using a platform-specific npx command. This represents standard dependency management within the author's own ecosystem and does not constitute a security risk.
Audit Metadata