run_sleuthkit · SIFTGuard MCP: Risk & Policy

WHAT IT DOES

What run_sleuthkit does on SIFTGuard

AI agents invoke run_sleuthkit to trigger actions in SIFTGuard. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_sleuthkit needs a policy

This is an Execute tool because it runs external commands/tools (Sleuthkit utilities) whose behavior and output depend on supplied arguments (disk image paths, options). While it is read-only in intent (forensic analysis), the execution of arbitrary Sleuthkit commands with attacker-controlled parameters could be misused to extract sensitive data, enumerate systems, or gather intelligence for further attacks.

From the tool's definition Tool description states it 'Run[s] Sleuthkit (fls/mmls/istat) to analyze disk images' — the verb 'Run' combined with execution of external forensic tools (fls, mmls, istat) that perform low-level filesystem operations on disk images indicates code/tool…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_sleuthkit Rate-limited

run_sleuthkit stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_sleuthkit": {
      "limits": [
        {
          "counter": "run_sleuthkit_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches SIFTGuard, so you can run agents against it safely.

FAQ

Questions about run_sleuthkit

What does the run_sleuthkit tool do? +

Run Sleuthkit (fls/mmls/istat) to analyze disk images. Reveals deleted files, filesystem metadata, partition tables. It is categorised as a Execute tool in the SIFTGuard MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_sleuthkit? +

Register the SIFTGuard MCP server in PolicyLayer and add a rule for run_sleuthkit: 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 SIFTGuard. Nothing to install.

What risk level is run_sleuthkit? +

run_sleuthkit is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_sleuthkit? +

Yes. Add a rate_limit block to the run_sleuthkit 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 run_sleuthkit completely? +

Set action: deny in the PolicyLayer policy for run_sleuthkit. 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 run_sleuthkit? +

run_sleuthkit is provided by the SIFTGuard MCP server (sodiq-code/siftguard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.