Skip to main content
Glama
Sign In

cloakcheck

by app.vercel.cloakcheck-wheat
OverviewDiscussionsAdmin

Server Details

Scan a page for hidden prompt-injection payloads targeting AI agents.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-03-26
URL
ChatGPT
–
Claude
–

TDQS

A4.2/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of misselection between tools. The tool's scope is crisply defined, explicitly excluding visible-body-text judgment.

Naming Consistency5/5

The single name check_page_for_injection follows a clear verb_noun pattern in snake_case. With only one tool there is no convention to break, and the name itself is predictable and descriptive.

Tool Count3/5

One tool for a narrowly scoped security scanner is defensible, but it is thin for a domain that naturally includes scanning raw text, HTML fragments, or batches of URLs. It sits at the borderline of being under-provisioned.

Completeness3/5

The tool covers the core check but leaves notable gaps: there is no way to scan raw text or an in-memory document, no batch/multi-URL scanning, and no structured reporting of which detection technique fired. Agents can work around these by looping calls, but coverage of the scanning lifecycle is partial.

Available Tools

1 tool
check_page_for_injectionAInspect

Scan a single web page for content planted to hijack an AI agent reading it -- invisible unicode (zero-width chars, the unicode 'tag' block used for steganographic prompt injection), CSS-hidden instruction text, and instruction-shaped language in alt/title/aria-label attributes a human would never read. Does NOT judge whether visible body text is safe -- only content hidden from normal human reading flow is flagged, so a page that legitimately discusses prompt injection won't false-positive on itself. Call this before an autonomous shopping/browsing agent acts on a page's content (add to cart, follow instructions found on the page, etc).

Inputs: url (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • GEO Shield MCP

      krishnaGauss
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to inspect websites read-only for manipulation aimed at search engines and AI assistants — sneaky and open redirects, hidden text and links, injected spam, hijacked metadata, and hidden prompt-injection or prefill-based recommendation poisoning — with every finding backed by deterministic rule evidence, severity, and remediation. Scans are stored locally, redirect chains can be traced hop-by-hop, and results can be exported as markdown or JSON reports.
      MIT

    • prompt-sanitizer

      daoudandiaye98-alt
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to scan untrusted web pages, emails, PDFs, and tool output for prompt injection across 17 languages, returning findings and cleaned text before the agent reads the content.
      MIT

    • SmuggleCheck

      miketusa-ctrl
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to scan text and compare strings for hidden prompt-injection content such as ASCII smuggling, zero-width or emoji steganography, bidirectional text tricks, and homoglyphs. It provides one detection layer, not a full defense against plainly written prompt injection.
      MIT

    • malskanner

      Octolabo
      A
      license
      Not graded
      quality
      C
      maintenance
      MCP server to scan a repository for hidden prompt injection payloads and return a REFUSE/WARN/OK verdict, allowing AI agents to gate their own trust.
      33 npm
      5
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources