The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and examples intended to guide an AI agent's writing style. No executable scripts (Python, Node.js, or shell) are included.
[PROMPT_INJECTION]: The skill uses persona-based framing ("You are representing Digital Speed") to align output with brand values. It does not attempt to bypass safety guidelines, disregard system instructions, or extract system prompts.
[SAFE]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill mentions competitors and the author's name in plain text without suspicious links.
[INDIRECT_PROMPT_INJECTION]: Although the skill is designed to process user-supplied content to rewrite it in the brand's voice, it lacks any tools or capabilities (such as network access or file system writes) that would allow an indirect injection to perform malicious actions.

brand-persona