The Agent Skills Directory

Prompt Injection (SAFE): The instructions focus entirely on UI design principles and do not contain any attempts to bypass safety filters or override system instructions.- Data Exposure & Exfiltration (SAFE): No network calls, credential patterns, or sensitive file path access were detected.- Obfuscation (SAFE): No Base64, zero-width characters, or other encoding techniques are used to hide content.- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not reference or install any external packages or scripts.- Privilege Escalation (SAFE): No commands or instructions for elevating system permissions are present.- Persistence Mechanisms (SAFE): No logic exists to modify system startup or maintain long-term access.- Metadata Poisoning (SAFE): Metadata fields are descriptive and accurately reflect the skill's UI design purpose.- Indirect Prompt Injection (SAFE): While the skill processes user design requirements, it lacks any high-risk capabilities (like command execution or file writing) that could be exploited via malicious input.- Time-Delayed / Conditional Attacks (SAFE): No time-based or environment-based conditional triggers are present.- Dynamic Execution (SAFE): No code generation or runtime evaluation logic is included.

ui-designer