git reset --hard (DESTRUCTIVE: discards commits and working-tree changes).
AI agents call git_reset_hard to permanently remove resources in LocalAnt — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
git reset --hard is an irreversible operation that destroys both staged and unstaged changes in the working tree and can rewrite commit history. Once executed, affected changes cannot be recovered without access to git reflog or backups.
From the tool's definition Tool name explicitly states 'git_reset_hard'; description explicitly states '(DESTRUCTIVE: discards commits and working-tree changes)'.
Attacks that exploit this kind of access
git reset --hard (DESTRUCTIVE: discards commits and working-tree changes). It is categorised as a Destructive tool in the LocalAnt MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LocalAnt MCP server in PolicyLayer and add a rule for git_reset_hard: 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_reset_hard is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the git_reset_hard 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_reset_hard. 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_reset_hard 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 →