frontend-design

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external design briefs to generate layout plans and frontend code, which is its primary function. While this creates a surface for indirect prompt injection, it is restricted to generating UI designs for the user.\n- Ingestion points: User-provided design briefs described in SKILL.md under the 'Process' section.\n- Boundary markers: The instructions do not define explicit delimiters to isolate the brief content from the agent's instructions.\n- Capability inventory: The skill generates HTML/CSS code, layout wireframes, and design plans; it also mentions taking screenshots if the environment supports it.\n- Sanitization: No explicit sanitization or validation of input brief content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:02 AM
Security Audit — agent-trust-hub — frontend-design