Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
70
87%
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
Low
Low-risk findings.
2 low severity findings. 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.
SKILL.md instructs the skill to fetch guidelines at runtime from a public URL (outsider-authored web content) and then apply the fetched rules—i.e., the fetched command.md text would be ingested into the LLM context for review.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill explicitly instructs fetching and using the remote content at https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md at runtime via WebFetch, and states the fetched file "contains all the rules and output format instructions" which directly control the agent's behavior.
04514f0
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.