The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown instructions and metadata. It does not include any shell commands, scripts, or binaries, posing no threat to the host system or execution environment.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined inputs such as brand names and visual references to generate image prompts. While this represents a potential attack surface for indirect prompt injection, the skill lacks high-privilege capabilities like network access or file system modification, which limits the potential impact to the quality and relevance of the generated image prompts.- [NO_CODE]: No code files, package manifests, or remote code patterns were found in the skill package. The instructions are purely textual and operate within the safety boundaries of the AI agent's prompt generation capabilities.

brandkit