More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    🕵️ Confusable Handle Detector

    1

    High-Stakes Handle Security In an era of sophisticated social engineering, a username that looks like "apple" might actually contain a Cyrillic "а" or a hidden zero-width joiner.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    🕵️ Confusable Handle Detector

    🕵️ Confusable Handle Detector

    Example session with this skill installed

    Check if the handle "pаypal" is spoofed or contains any suspicious characters.

    • Read your context and instructions
    • Compiled the confusable handle detector

    Findings: [HIGH]

    • Rule: homoglyph-detected (ID: CH04)
    • Evidence: 'а' (U+0430) is Cyrillic Small Letter A, visually identical to Latin 'a'.

    Remediation

    Flag as high-risk spoofing attempt. Recommend blocking handle registration to prevent brand impersonation.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    High-Stakes Handle Security

    In an era of sophisticated social engineering, a username that looks like "apple" might actually contain a Cyrillic "а" or a hidden zero-width joiner. The Confusable Handle Detector is a specialized security tool designed for developers, community managers, and security researchers to audit strings for Unicode-based spoofing attempts.

    What it does

    This skill performs deep inspections on handles, brand names, and text lists to identify:

    • Invisible Characters: Zero-width spaces and joiners that hide in plain sight.
    • Homoglyphs: Look-alike characters from different scripts (e.g., Latin 'o' vs. Greek 'ο').
    • Directional Overrides: RTL/LTR markers used to flip the display order of characters.
    • Mixed-Script Detection: Identifying suspicious script switching within a single word.

    Why use this skill

    Writing your own regex to catch every Unicode edge case is error-prone and time-consuming. This skill leverages a pre-built Python scanner and a curated reference library to provide instant, structured auditing. It moves beyond simple "Is this valid?" checks to "Is this deceptive?", providing actionable remediation snippets that help you explain risks to users or stakeholders without sounding alarmist.

    The Output

    Each scan produces a detailed report covering the scope inspected, a categorized list of findings by severity, and specific remediation advice based on JustHandled Labs' audit checklist.

    Mixed-script and non-ASCII detection are heuristics, so a legitimate non-Latin brand will trip those rules, which is why they are advisory rather than hard failures. It flags suspicious characters; it does not decide intent.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    **/*.txt
    --handle
    <name>
    --stdin

    Read-only. Inspects each character against the Unicode database in the standard library. Reads no environment variables and writes nothing.

    Listed5 months ago
    Updated19 days ago

    What's inside

    Frequently Asked Questions

    This skill detects invisible zero-width characters, right-to-left override markers, and 'homoglyphs'—characters from different alphabets that look identical to the naked eye but are computationally different.

    It is designed for any AI agent capable of processing text strings, making it ideal for integration into security bots, community moderation workflows, or automated brand-monitoring agents.

    Unlike basic sanitization, this skill provides a detailed severity report and specific remediation advice, explaining exactly why a handle is suspicious and how to address it.

    Your purchase includes the full skill logic, a curated reference library of deceptive characters, and ongoing access to any logic refinements or script updates released by the developer.

    Yes, the skill is optimized for batch processing, allowing you to scan long lists of usernames or brand strings to identify high-risk entries in a single pass.

    New in Security