根据 git 缓存区(staged)内容生成中文提交消息草稿。无参数时只看缓存区、不执行 git add;带参数 `/msg X` 时先把与 X 相关的改动 `git add` 到缓存区,再生成消息草稿。始终不执行 git commit。
83%
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.
SKILL.md 的运行流程在“生成消息步骤”中执行 `git diff --cached` 读取缓存区的具体改动内容(可能包含由其他人提交的代码/文本),并将该 diff 作为可读文本进入 LLM 上下文用于生成提交消息,从而存在外部自由文本注入风险。
baojie/shiji-kb
6b836e3
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.