icon-brief-writer
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and packaged content focus entirely on design documentation and UI/UX best practices. No malicious behaviors or security risks were identified.
- [PROMPT_INJECTION]: No evidence of jailbreak attempts, system prompt extraction, or safety filter bypasses. The 'Critical rules' section contains standard instructional guidance for maintaining quality and relevance.
- [DATA_EXFILTRATION]: No patterns for reading sensitive files (e.g., .env, .ssh, .aws) or sending data to external endpoints were found. The skill operates purely within the text-based interaction context.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation attempts were detected in the skill instructions or the associated binary package.
- [EXTERNAL_DOWNLOADS]: The skill mentions established open-source icon libraries such as Heroicons, Lucide, and Phosphor Icons as recommendations for users. These are well-known, trusted resources and are not used for automated downloads or runtime execution.
- [OBFUSCATION]: The '.skill' file is a standard ZIP archive containing the skill markdown. No hidden commands, encoded URLs, or homoglyph attacks were found within the binary or text content.
Audit Metadata