code-native-ui-ideation
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any detected malicious patterns, obfuscation, or dangerous command executions. It focuses on UI design exploration within existing project development surfaces.
- [DATA_EXFILTRATION]: The instructions proactively address data security by requiring the use of synthetic, sanitized, or safely derived fixtures and strictly prohibiting the use of sensitive production data in development stories or previews.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests external project data (e.g., design systems, fixtures, and source code) to generate UI variants.
- Ingestion points: Project source code, design system documentation, and data fixtures as specified in the "Build variants" section of SKILL.md and the platform reference files.
- Boundary markers: None identified for prompt isolation.
- Capability inventory: File system modification and shell command execution for building and rendering UI variants in simulators or browsers, as referenced in platform-specific guides.
- Sanitization: The skill explicitly requires the use of sanitized fixtures to mitigate data-related risks.
Audit Metadata