Review changes to carnival games against the house rules in AGENTS.md. Use on pull requests that add or change a game under src/games/.
93%
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 reviews pull requests, which involve reading external PR content and outsider-authored code and text.
guypod/carnival-evolution-20261028
68862bd
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.