save_attack_preset

THE RISK

Medium Risk

Why save_attack_preset needs a policy

This is a Write operation because it creates or stores configuration data (a preset) that can be reused later. It is reversible—presets can be deleted or overwritten. While it supports hashcracking activities (a security assessment context), the tool itself only manages configuration metadata, not executing attacks or destroying data.

From the tool's definition The tool 'save_attack_preset' saves (creates/stores) attack configuration data as a preset for reuse. The verb 'save' indicates data creation or modification in persistent storage.

Documented attack patterns abuse exactly the kind of access save_attack_preset gives an agent:

POLICY

How to control save_attack_preset

PolicyLayer is an MCP gateway — it sits between your AI agents and Hashcat MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for save_attack_preset:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_attack_preset": {
      "limits": [
        {
          "counter": "save_attack_preset_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

save_attack_preset stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Hashcat MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Hashcat MCP Server tools

Execute auto_attack_strategy Automatically choose and execute best attack strategy Execute benchmark_hashcat Run hashcat benchmark for specified hash types or all types Execute crack_hash Crack a hash using hashcat with various attack modes Execute crack_multiple_hashes Crack multiple hashes efficiently with auto-detection Execute create_wordlist_rules Generate wordlist variations using hashcat rules Execute generate_mask_attack Generate mask attack patterns for brute force Execute generate_smart_masks Generate intelligent mask patterns based on common password patterns Write create_session Create a new hashcat session for tracking

All 23 Hashcat MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about save_attack_preset

What does the save_attack_preset tool do? +

Save attack configuration as preset. It is categorised as a Write tool in the Hashcat MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_attack_preset? +

Register the Hashcat MCP Server MCP server in PolicyLayer and add a rule for save_attack_preset: 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 Hashcat MCP Server. Nothing to install.

What risk level is save_attack_preset? +

save_attack_preset is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_attack_preset? +

Yes. Add a rate_limit block to the save_attack_preset 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.

How do I block save_attack_preset completely? +

Set action: deny in the PolicyLayer policy for save_attack_preset. 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.

What MCP server provides save_attack_preset? +

save_attack_preset is provided by the Hashcat MCP Server MCP server (mordavid/hashcat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Hashcat MCP Server tool call.

Start from Hashcat MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →