The Agent Skills Directory

[SAFE]: The skill gathers inputs from specific project files (brand-kit.md, about-me.md, thumbnail-config.md) to personalize the thumbnail generation. These files are related to the skill's primary purpose of branding.
[SAFE]: No remote code execution, external downloads, or network exfiltration patterns were detected. The skill only generates text prompts for the user to copy and use in an external image generation tool.
[SAFE]: No obfuscation or malicious prompt injection patterns designed to bypass safety filters were found. The 'CRITICAL' instruction in the body is a control flow directive for the agent's startup behavior, not a safety override.

youtube-thumbnail