The Agent Skills Directory

[SAFE]: The skill serves as a documentation resource for SEO specialists, providing templates for standard web development tasks such as meta tag configuration and JSON-LD generation.
[DATA_EXPOSURE]: The skill uses clear placeholders like VERIFICATION_CODE and BING_VERIFICATION_CODE for site verification settings. It follows security best practices by recommending the use of environment variables and runtime configurations to avoid hardcoding sensitive values.
[UNVERIFIABLE_DEPENDENCIES]: References to external modules such as @nuxtjs/sitemap, @nuxtjs/robots, and @nuxt/image target well-known, official, or community-standard packages within the web development ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates ingesting content from external APIs (e.g., fetchArticle(slug)) to populate SEO metadata and JSON-LD scripts. While this represents an attack surface for indirect prompt injection from malicious external data, the pattern follows industry-standard implementation for SEO automation and includes no dangerous autonomous execution capabilities. The risk is assessed as safe given the documentation context.
Ingestion points: External data is fetched in pages/blog/[slug].vue and app/blog/[slug]/page.tsx.
Boundary markers: None explicitly shown for data contents.
Capability inventory: Metadata generation and script tag injection.
Sanitization: Standard serialization is used for structured data.

seo-optimization