The Agent Skills Directory

[SAFE]: The skill serves as a configuration reference for the Unlayer email and page builder, providing standard API usage examples and implementation patterns.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for handling dynamic content through merge tags and display conditions, which involve processing external data.
Ingestion points: Dynamic content is ingested via unlayer.setMergeTags, unlayer.setDesignTags, and unlayer.setDisplayConditions as described in SKILL.md.
Boundary markers: The skill utilizes template engine syntax (e.g., {{var}}, {% if %}) as delimiters for dynamic content.
Capability inventory: The skill demonstrates network capabilities through fetch and XMLHttpRequest for image uploads and browsing, but these are constrained to local or relative API endpoints.
Sanitization: The skill proactively addresses security risks by documenting the safeHtml feature, which uses DOMPurify to sanitize HTML output and mitigate XSS vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill includes an example for loading custom fonts from Google Fonts (fonts.googleapis.com), which is a recognized and trusted service.
[CREDENTIALS_UNSAFE]: While the skill references sensitive keys (Project Secret, Cloud API Key), it correctly uses placeholders like YOUR_PROJECT_SECRET and includes clear warnings to never expose these secrets in frontend code, directing users to perform sensitive operations server-side.

unlayer-config