The Agent Skills Directory

[Prompt Injection] (SAFE): The content consists of meta-instructions for task management and workflow optimization. There are no attempts to override safety filters, bypass constraints, or extract system prompts.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns were detected. The skill does not access the filesystem or the network.- [Remote Code Execution] (SAFE): The skill contains no executable code, scripts, or shell commands. It is entirely instructional markdown.- [Persistence & Privilege Escalation] (SAFE): No commands for modifying system configurations, installing services, or maintaining unauthorized access were found.- [Indirect Prompt Injection] (SAFE): While the skill defines how to process other skills, it does not ingest untrusted external data or provide a surface for third-party instruction injection.

using-superpowers