github-worktree
须用户 @ 本 skill 或明确说要按 GitHub Issue worktree 流程执行时再读取。 在 master 上：确定关联的 GitHub Issue（默认关联已有，明确要建时才在上游建单）、生成分支名、git fetch、脚本同时创建新分支与 worktree、cursor --new-window 打开新窗口；细节与分支命名见正文。 不因泛泛提到 GitHub、issue、worktree、建分支等词而自动套用。
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
SKILL.md 在 Step 2/Step 3 通过 GitHub MCP（user-github 的 issue_read/issue_write）读取/生成的 Issue 标题、标签与正文（outsider 作者的 issue 内容或用户在公开仓库创建/确认的正文）会进入代理推理与后续分支名生成流程，从而把可包含注入文本的自由文本喂入 LLM 上下文（间接提示注入风险）。
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly runs "git remote set-url origin https://github.com/TencentBlueKing/bk-ci.git" and "git fetch origin master" at runtime, fetching repository content (including .cursor configs and gradle wrappers) that the scripts copy/run (e.g., Sync-ConfigDirectory and Invoke-AllJooq), so the remote URL https://github.com/TencentBlueKing/bk-ci.git is a runtime dependency that can deliver and cause execution of remote code/config.
- Repository
- TencentBlueKing/bk-ci
- Commit
94743cb
- 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.