Skip to main content
Glama

scan_backdoors

Read-only

Deep-scan a Roblox place for backdoors, exploits, and obfuscation across script source and hidden instance attributes, then rank findings by severity.

Instructions

Tufan Power Tool: deep-scan a place for backdoors / exploits / obfuscation. Checks script source (require-of-Value, require-by-asset-id, loadstring, HttpGet, getfenv, exploit APIs, Discord webhooks, anti-debug, high-entropy blobs) AND the spots a script-only scanner misses — instance attributes and StringValues hiding encoded payloads. Findings sorted high→low severity. NOTE: this scans the PLACE tree; it cannot read installed Studio plugins' own source (a Roblox limit) — use list_studio_plugins to see what plugins are installed (the remote-code-plugin vector).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
rootPathNoLimit scan to a subtree (default: whole place)
severityNoOnly show findings at/above this severity

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's extra value is in scope and limits: it discloses that findings are sorted high→low severity and, importantly, that it cannot read installed Studio plugins' own source due to a Roblox platform limit. That limitation disclosure is exactly the kind of behavioral context annotations cannot convey, though return shape itself is left implicit (no output schema).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause, followed by the detection surface and the caveat. The long parenthetical enumeration of checks is dense but each item earns its place by telling the agent what the scanner covers; wording could be trimmed slightly but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-optional-parameter read-only scan tool, the description covers scope (whole place vs subtree vs severity threshold), detection coverage, result ordering, and the plugin blind spot with an alternative. Only the result payload shape is unaddressed, which is acceptable given there is no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so place, rootPath, and severity are already documented including defaults and the enum. The description's only added signal is the severity ordering of results, which is more output behavior than parameter meaning, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('deep-scan a place for backdoors / exploits / obfuscation') and then enumerates exactly what is inspected (require-by-asset-id, loadstring, HttpGet, getfenv, webhooks, anti-debug, entropy blobs, instance attributes, StringValues). The contrast with 'a script-only scanner' plus the explicit mention of list_studio_plugins makes it distinguishable from siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for when to reach for this tool (deep place scan for malicious/obfuscated content) and routes the agent elsewhere for the plugin-source case by naming list_studio_plugins. It stops short of stating explicit exclusions or when a lighter scan would suffice, so it is clear but not fully prescriptive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.