Define or review a visual system, DESIGN.md, or redesign direction. Use for typography, layout, color, motion, and interaction design decisions.
83%
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 required workflow loads third-party supplier skill bundles from public GitHub repositories and, when a vendor seed is requested, a public npm package template, both of which are community-authored and read by the agent after it actively selects and fetches them, so the exposure is low rather than medium.
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 decisive dependency is the getdesign npm package, fetched from registry.npmjs.org and executed via `bunx`, whose publisher is never established and whose hash is checked only against the same registry's manifest, so it is weak/unknown provenance and the tier is high; the Interface Design, Taste, and Impeccable GitHub repositories loaded via the Skills CLI are individual-owned, so they would be medium on their own, and the official Stitch endpoint is strong.
first-fluke/oh-my-agent
8a03eb1
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.