检查本地 Git 仓库状态，仅执行白名单 git 命令。
AI agents call inspect_local_repo to retrieve information from PRPilot MCP Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves repository metadata and state without modifying data. The explicit mention of whitelisted commands strongly suggests safe, read-only git operations. Even though git commands could theoretically be dangerous, the whitelist mechanism prevents execution of destructive or write operations. The blast radius of misuse is minimal—an agent gains visibility into local repo state but cannot change it.
From the tool's definition Tool description states it 'inspects local Git repository status' and 'only executes whitelisted git commands' (检查本地 Git 仓库状态，仅执行白名单 git 命令).
Attacks that exploit this kind of access
检查本地 Git 仓库状态，仅执行白名单 git 命令。. It is categorised as a Read tool in the PRPilot MCP Agent MCP Server, which means it retrieves data without modifying state.
Register the PRPilot MCP Agent MCP server in PolicyLayer and add a rule for inspect_local_repo: 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 PRPilot MCP Agent. Nothing to install.
inspect_local_repo 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 inspect_local_repo 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 inspect_local_repo. 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.
inspect_local_repo is provided by the PRPilot MCP Agent MCP server (we1chan/prpilot). 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 →