Create a clean modern design system with a luminous blue sky atmosphere, soft drifting cloud light, minimal white framing, and serene premium typography.
49
53%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./agent-skills/web-design/blue-cloudy-clean-modern/SKILL.mdLow
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
This skill’s demo runtime (demo/index.html) decodes and injects a long HTML string (encodedHtml decoded via `TextDecoder`/`atob`) into an iframe (`frame.srcdoc = source`), which is then parsed as HTML; that HTML includes arbitrary text/content, so outsider-authored free text can enter the LLM/agent context through the rendered document or embedded runtime behaviors.
46abf78
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.