查看工作区状态 (git status)
AI agents call git_status to retrieve information from Git Commit MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
git_status is a read-only operation that queries repository state. It has no side effects, does not modify files or repository history, and simply provides information about what has changed. This is a classic Read category tool with low severity since it cannot cause damage or unexpected effects.
From the tool's definition Tool name is 'git_status' and description indicates it performs 'git status' operation, which retrieves and displays the current state of the working directory (modified files, staged changes, untracked files) without modifying any data.
Attacks that exploit this kind of access
查看工作区状态 (git status). It is categorised as a Read tool in the Git Commit MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Git Commit MCP Server MCP server in PolicyLayer and add a rule for git_status: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git Commit MCP Server. Nothing to install.
git_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the git_status rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for git_status. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
git_status is provided by the Git Commit MCP Server MCP server (lenslp/git-commit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →