The Agent Skills Directory

[SAFE]: The skill follows secure practices by performing content extraction and normalization on user input before using it to generate image prompts. It includes explicit negative constraints (e.g., 'no Logo', 'no real people', 'no watermark') to prevent the generation of potentially infringing or unsafe content. The use of the internal image_gen tool is well-scoped within the skill's intended purpose. No indicators of prompt injection, data exfiltration, or unauthorized command execution were found.

blue-white-minimal-enterprise-ppt