Security audit
Security checks for vulnerabilities and agentic risk
This git workflow skill is not malicious, but it asks for broad command execution around repository-changing actions without narrow triggers or clear confirmation controls.
Review this before installing if you do not want a skill to run git commands or create commits, branches, tags, merges, or rollbacks from broad prompts. Use it only with explicit user-directed git tasks and confirm the target repository and operation before allowing state-changing commands.
The usage guidance says to use this skill for 'any code change' and broadly for efficiency, automation, batch processing, and workflow optimization, which greatly over-expands the activation scope. Because the skill advertises automated commits, branching, tagging, and uses exec, this can cause the agent to select it in situations where git actions are not appropriate or not yet authorized.
The trigger condition '当用户需要执行相关操作时自动触发' is so broad that it can cause the skill to activate for vague or loosely related requests. In a skill with exec capability and repository-affecting behavior, unintended invocation increases the chance of unauthorized command execution, accidental git operations, or acting on ambiguous user intent.
The description states '支持中文交互' in a way that presents a language constraint or default without offering a user opt-in or alternative locale choice. Under the policy, forcing a specific language without user choice can be a natural-language policy violation unless clearly justified as region-specific.
No suspicious patterns detected.
