The Agent Skills Directory

Prompt Injection (SAFE): No instructions found that attempt to override safety filters, bypass system prompts, or use role-play for jailbreaking purposes.- Data Exposure & Exfiltration (SAFE): No access to sensitive file paths, hardcoded credentials, or network exfiltration patterns detected.- Remote Code Execution & Dependencies (SAFE): No use of package managers, remote script downloads, or dynamic code execution blocks.- Obfuscation (SAFE): No use of Base64, zero-width characters, homoglyphs, or encoded strings intended to hide malicious intent.- Privilege Escalation & Persistence (SAFE): No commands related to elevated permissions (sudo) or maintaining access (cron, shell profiles).- Indirect Prompt Injection (LOW/SAFE): The skill prompts users to provide external links and creative work for analysis. While this is a common input surface for indirect injection, the skill does not possess any dangerous capabilities (like file writing or command execution) that could be exploited through these inputs.

creative-design