The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from URL query parameters, which creates a surface for indirect prompt injection.\n
Ingestion points: app/page.tsx reads parameters such as live_preview and entry_uid directly from searchParams.\n
Boundary markers: The skill does not define specific boundaries or markers to isolate the fetched data from the agent's internal instructions.\n
Capability inventory: The skill utilizes @contentstack/delivery-sdk to fetch and render content based on these parameters.\n
Sanitization: The skill includes isomorphic-dompurify, which helps sanitize external content before rendering.\n- [EXTERNAL_DOWNLOADS]: The skill specifies dependencies from the official vendor ecosystem and community-maintained utilities.\n
Downloads include @contentstack/delivery-sdk, @contentstack/live-preview-utils, and @timbenniks/contentstack-endpoints.\n- [CREDENTIALS_UNSAFE]: The skill uses environment variables for authentication.\n
The instructions use the NEXT_PUBLIC_ prefix for variables like NEXT_PUBLIC_CONTENTSTACK_DELIVERY_TOKEN, which exposes these values to the client-side environment by design in Next.js frameworks.

contentstack-kickstart