build-review-interface
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is instructional and focuses on UI/UX design for a local development tool.
- [INDIRECT_PROMPT_INJECTION]: The interface is designed to display untrusted LLM traces.
- Ingestion points: Data enters the tool via local JSON or CSV files.
- Boundary markers: The instructions focus on native data rendering and visual hierarchy.
- Capability inventory: Capabilities are limited to local file operations and browser-based display.
- Sanitization: The skill explicitly mandates sanitizing LLM outputs by stripping HTML and disabling images to mitigate risks from malicious data or tracking pixels.
Audit Metadata