Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode)
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 skill uses WebSearch and WebFetch tools to fetch web pages based on user input or research tasks, representing low-risk outsider-authored text exposure.
open-gsd/gsd-core
99bbbac
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.