AI agents call git_clean_preview to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to preview the effects of a git clean operation (which removes untracked files) rather than execute it. Preview operations are typically read-only and non-destructive. However, confidence is moderate (0.7) because the description is incomplete ('Preview files that' cuts off), leaving some ambiguity about the actual scope and whether it might have side effects.
From the tool's definition Tool name is 'git_clean_preview' and description begins 'Preview files that' — the 'preview' verb and incomplete description suggest this is a read-only operation that shows what would be deleted without actually deleting.
Attacks that exploit this kind of access
Preview files that. It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for git_clean_preview: 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 LocalAnt. Nothing to install.
git_clean_preview 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_clean_preview 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_clean_preview. 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_clean_preview is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →