frontend-design

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): The use of 'CRITICAL' and 'IMPORTANT' is strictly within the context of design instructions and does not attempt to bypass agent safety filters or override system instructions.
  • [Data Exposure & Exfiltration] (SAFE): No patterns for accessing sensitive files (e.g., .ssh, .aws) or exfiltrating data via network requests were found.
  • [Unverifiable Dependencies] (SAFE): The skill mentions the 'Motion' library for React, which is a standard design dependency. No malicious installation patterns or remote script executions are present.
  • [Indirect Prompt Injection] (LOW):
  • Ingestion points: User-provided frontend requirements (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Code generation (HTML/CSS/JS/React). No subprocess, filesystem, or network capabilities.
  • Sanitization: None identified.
  • [Trusted Source] (INFO): The skill is hosted under 'github.com/anthropics/skills', which is a recognized trusted organization and repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 03:47 PM