The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown documentation providing architectural guidance for web development. No executable scripts, command-line operations, or persistence mechanisms are included.
[INDIRECT_PROMPT_INJECTION]: The skill documents an implementation pattern where dynamic content (such as blog titles or slugs) is accepted via URL query parameters for image rendering. While this describes an ingestion point for untrusted data in the resulting application, the instructions themselves are standard development practices and do not contain malicious patterns or exploit vectors targeting the agent.
[EXTERNAL_DOWNLOADS]: The documentation mentions using fetch to load avatar images or logos for rendering. This is a standard functional requirement for the described feature and does not involve downloading untrusted executable code or scripts.

og-images