The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and checklists aimed at optimizing web content for search engines and readability. It does not include any scripts, external dependencies, or command execution capabilities.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and edit web content (marketing copy, blog posts, etc.), which creates a theoretical attack surface for indirect prompt injection if the content being processed contains malicious instructions. However, the skill does not define any dangerous tools or system access that could be exploited through such an injection, and its impact is limited to the text generation output.
[PROMPT_INJECTION]: The skill uses strong instructional language (e.g., 'Operational Directive', 'NEVER use the following AI hallmark words') to guide the agent's behavior. These are stylistic constraints relevant to the skill's purpose (SEO and human-like writing) and do not attempt to bypass core AI safety filters or extract system prompts.

seo