# rm

Delete file/directory. Auto-selects client.

Agent View of the PolicyLayer registry record for `rm`. HTML page: https://policylayer.com/tools/0xyg3n-claude-c2/rm

## Facts

- Tool: `rm`
- Server: Claude C2 (`0xyg3n/claude-c2`) — https://policylayer.com/tools/0xyg3n-claude-c2.md
- Homepage: https://github.com/0xyg3n/claude-c2
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "rm",
    "arguments": {}
  }
}
```

## Why rm is rated Critical

File and directory deletion is inherently destructive and cannot be undone. Given the MCP context where an AI agent could invoke this tool based on natural language commands, a misused 'rm' command could delete critical system files, user data, or entire directory structures across the connected remote system. This represents maximum severity due to irreversibility and potential for widespread unintended data loss.

From the tool's own definition: "Tool name 'rm' combined with description 'Delete file/directory' directly indicates irreversible removal of files or directories. The 'Auto-selects client' phrasing suggests it operates across the remote system without requiring explicit path confirmation."

## Use case

AI agents call rm to permanently remove resources in Claude C2, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Claude C2:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "rm"
  ]
}
```

## Other tools on Claude C2 (93)

- `kill` — Destructive — https://policylayer.com/tools/0xyg3n-claude-c2/kill.md
- `mv` — Destructive — https://policylayer.com/tools/0xyg3n-claude-c2/mv.md
- `persist_remove` — Destructive — https://policylayer.com/tools/0xyg3n-claude-c2/persist-remove.md
- `reg_delete` — Destructive — https://policylayer.com/tools/0xyg3n-claude-c2/reg-delete.md
- `timestomp` — Destructive — https://policylayer.com/tools/0xyg3n-claude-c2/timestomp.md
- `amsi_bypass` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/amsi-bypass.md
- `bypassuac` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/bypassuac.md
- `defender_exclude` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/defender-exclude.md
- `etw_patch` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/etw-patch.md
- `execute_assembly` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/execute-assembly.md
- `firewall_rule` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/firewall-rule.md
- `generate_payload` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/generate-payload.md
- `get_payload` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/get-payload.md
- `getsystem` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/getsystem.md
- `inject` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/inject.md
- `keylog_start` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/keylog-start.md
- `keylog_stop` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/keylog-stop.md
- `mcp_add_tool` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/mcp-add-tool.md
- `mcp_append_code` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/mcp-append-code.md
- `mcp_restart` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/mcp-restart.md
- `mimikatz` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/mimikatz.md
- `persist_registry` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/persist-registry.md
- `persist_schtask` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/persist-schtask.md
- `persist_service` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/persist-service.md
- `persist_startup` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/persist-startup.md
- `persist_wmi` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/persist-wmi.md
- `portscan` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/portscan.md
- `powershell` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/powershell.md
- `privesc_check` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/privesc-check.md
- `psexec` — Execute — https://policylayer.com/tools/0xyg3n-claude-c2/psexec.md
- …and 63 more: https://policylayer.com/tools/0xyg3n-claude-c2.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0xyg3n-claude-c2 · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xyg3n-claude-c2