icon-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious patterns or security vulnerabilities were identified in the skill. The instructions focus on UI design, icon mapping, and generating standard code integration templates (React, Vue, HTML).
- Data Handling (SAFE): The skill reads from its own memory files (
icon_mappings.md,library_preferences.md) and writes documentation to a local directory (/claudedocs/). No sensitive file access or network exfiltration patterns were found. - Indirect Prompt Injection (LOW): The skill ingests untrusted UI concepts and project data (Step 1). While it lacks explicit boundary markers or sanitization, it has no dangerous capabilities such as shell execution or network access, limiting the potential impact of such an attack to the generated documentation output.
Audit Metadata