ln-13-interaction-design-builder
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: Processes user-supplied scenarios, existing design files, and dynamic browser/screenshot content (SKILL.md).
- Boundary markers: Not explicitly defined for separating untrusted design inputs from agent instructions.
- Capability inventory: The agent is authorized to use browser tools, capture screenshots, and write to local document or diagram files (SKILL.md).
- Sanitization: The skill includes defensive instructions to prevent exposing sensitive internal information in feedback states and requires labeling of simulated data.
Audit Metadata