Collect GitHub repo health/usage stats into merged JSON.
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 script fetches repository metadata, releases, paths, and user profiles (company/location) from GitHub API endpoints via the `gh` CLI, which can include user-supplied profile text.
griddynamics/rosetta
ee7166a
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.