The canonical home for this skill is implement in agranado2k/google-books-clojure
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 takes a ticket body (a GitHub-hosted issue from /to-tickets, or a spec) as its primary input, and step 9 hands a PR to an automated reviewer, both of which an outsider can write to through public issue or PR comment surfaces without the agent selecting a specific item.
agranado2k/tic-tac-toe-haskell
7554191
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.