Create device-framed screenshots, product images, videos, or live UI mockups. Use when placing an image, recording, webpage, or component inside a phone, foldable, tablet, watch, laptop, monitor, or browser frame, including App Store-style visuals and launch videos.
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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.
The workflow renders a user-supplied screenshot, recording, page, or component into a device frame, and the attacker cannot force delivery, so any outsider text would arrive only through an arbitrary URL the user selects (the "embedding pages" guidance at lines 15-16 and 39).
ibelick/ui-skills
347d318
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.