The Agent Skills Directory

[SAFE]: The skill contains architectural instructions for Next.js App Router and Live Preview. No malicious behavior, exfiltration patterns, or obfuscation were found.
[NO_CODE]: The skill consists only of instructional markdown and does not include any executable scripts or binary files.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes data from an external CMS.
Ingestion points: Data is ingested from Contentstack via getPage and the ContentstackLivePreview.onEntryChange event listener.
Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are defined.
Capability inventory: The agent renders UI components and handles preview state based on the ingested external data.
Sanitization: The instructions explicitly mandate the use of isomorphic-dompurify to sanitize HTML content before rendering with dangerouslySetInnerHTML, effectively mitigating injection risks.

next-app