styleseed-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely instructional set of guidelines for performing design reviews. It analyzes UI/frontend code provided in the project context against a design rubric to suggest improvements.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied frontend code files as its primary input.
- Ingestion points: UI code files (React, Tailwind, HTML) read from the local directory.
- Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: The skill is limited to reading files and generating textual reports; it lacks capabilities for file-write, network exfiltration, or shell execution in its current instruction set.
- Sanitization: No input sanitization is performed on the analyzed code.
- [EXTERNAL_DOWNLOADS]: The skill includes documentation links to a GitHub repository (
github.com/bitjaru/styleseed) for referencing the full design rule set. These are standard informational links and do not involve automated downloads or runtime execution.
Audit Metadata