design-system-architecture
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized behaviors were detected. The skill instructions focus entirely on design system methodology and auditing.
- [EXTERNAL_DOWNLOADS]: The skill references an evaluation JSON file hosted on GitHub within the author's repository. This link is used for documentation and grading purposes and points to a well-known service.
- [PROMPT_INJECTION]: The skill involves an indirect prompt injection surface as it is designed to audit local project files.
- Ingestion points: The agent is instructed to inventory and audit local tokens, components, and variants (SKILL.md).
- Boundary markers: None present to delimit external file content from instructions.
- Capability inventory: Uses Read and Grep tools to analyze file contents (SKILL.md).
- Sanitization: No sanitization or validation of the ingested file content is specified. This surface is inherent to the skill's primary function as an auditing tool and is considered safe given the limited scope of the tools used.
Audit Metadata