Skip to main content
Glama

Prompt Sanitizer — prompt-injection scan for untrusted content

Prompt-injection quick scan (free)

input_guard_preview
Read-only

Free prompt-injection quick scan for untrusted input: up to 4,000 characters of text, or one https page, checked for hidden instructions aimed at agents (role override, invisible Unicode, hidden HTML) in 17 languages incl. Chinese, Japanese, Korean, Hindi, Arabic. Returns verdict, score and the top 3 findings. After: input_guard for every finding and the cleaned text.

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": "input_guard_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
textNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, and the description adds real value beyond them: input caps, the 17-language coverage, the specific detection categories (role override, invisible Unicode, hidden HTML), and the shape of the response (verdict, score, top 3 findings). It does not say what happens on fetch failure for the URL or that only the top 3 of possibly many findings are returned with the remainder dropped — worth noting but minor.

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?

Two sentences, front-loaded, with each clause carrying a concrete constraint or capability. The trailing 'After: input_guard for every finding and the cleaned text.' is telegraphic to the point of slight ambiguity about sequencing, 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?

With no output schema, the description correctly compensates by naming the return fields (verdict, score, top 3 findings). Combined with the stated input limits and the escalation path to input_guard, an agent has enough to call this correctly; only the both-parameters case and error behavior are unaddressed.

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 0% for the two parameters, so the description must carry the weight. It does clarify that 'text' is untrusted input capped at 4,000 characters and 'url' is a single https page to be fetched, but it largely restates the schema's maxLength/pattern constraints and never says whether the two are mutually exclusive or whether both may be supplied in one call.

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+resource ('prompt-injection quick scan for untrusted input') plus its scope limits (4,000 chars or one https page) and the exact threat classes it looks for. The word 'quick' and the free-tier framing distinguish it from the sibling input_guard without needing to open either 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 a clear workflow: run this preview first, then 'After: input_guard for every finding and the cleaned text' — an explicit next-step routing to the sibling. It does not state the inverse condition (e.g. that inputs over 4,000 characters must skip the preview and go straight to input_guard), so the exclusion side is only inferable from the stated limit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.