Create commits and pull requests for current git work. Use when the user wants to commit changes, open a pull request, or refresh a branch PR.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
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.
Third-party content exposure detected (high risk: 0.80). The skill explicitly uses the GitHub CLI to inspect remote PRs and repository files (e.g., "gh pr view", "gh repo view" and following <cwd>.github/pull_request_template.md) which are user-generated/untrusted third-party content that the agent reads and uses to shape PR titles/bodies and decision-making.
bc6a504
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.