Use when changing or migrating the shared require-no-mistakes PR-enforcement action, its live PR lookup, or its workflow caller.
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 workflow reads PR body content via a live GitHub REST API call (`/pulls/{number}`), which allows any outsider who creates a pull request to supply arbitrary free text into the monitored input path.
kunchenguid/no-mistakes
3d2d4bf
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.