github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain. Use whenever the user is creating, editing, or pushing a PR to a third-party GitHub repo — even if they just say "submit a PR", "open a PR", "fix this upstream", "rebase against main", "respond to the bot review", or names a target repo in the form `owner/repo`. Covers project discovery, CONTRIBUTING.md compliance, PR-size sanity check, minimal-diff implementation, isolated GUI E2E verification, PR description writing with AI-assisted disclosure, conflict resolution with fixup + autosquash, and post-submission bot/maintainer interaction. Also triggers on Chinese phrases like "提 PR"、"上游 PR"、"贡献代码"、"rebase 冲突"、"PR 描述写不好"、"回应维护者"、"AI 贡献声明".
75
92%
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.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
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.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The playbook explicitly requires fetching and reading untrusted, public repository content (e.g., reading each target repo's CONTRIBUTING.md and using gh pr list / gh pr view on arbitrary owner/repo targets and PR pages on GitHub), and it instructs the agent to act on those findings (e.g., add AI disclosure, change workflow), so third-party content can materially influence tool use and decisions.
- Repository
- daymade/claude-code-skills
- Commit
bbf87f3
- Audited
- Security analysis
Is this your skill?
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.