More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    📢 AI Disclosure Linter

    2

    Regulators and ad platforms stopped treating AI disclosure as optional, and the gaps that get flagged are almost never loud.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    📢 AI Disclosure Linter

    📢 AI Disclosure Linter

    Example session with this skill installed

    Scan my marketing site and react components to see if our new chatbot and AI-generated hero images need disclosures.

    • Read your context and instructions
    • Compiled the ai disclosure linter

    Found 3 issues:
    [ADL001] src/App.tsx:142 - Found <ChatWindow> without nearby AI-interaction disclosure.
    [ADL002] public/hero.png - AI-generated media missing visible label.
    [ADL006] docs/affiliate.md - Disclosure wording is buried in footer; consider moving it higher.

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

    About this skill

    Regulators and ad platforms stopped treating AI disclosure as optional, and the gaps that get flagged are almost never loud. They are a chat widget that never says it is a bot, an AI-generated image with no label, ad copy written by a model with nothing telling the reader so, and a sponsored post missing its material-connection line.

    This skill reads your code and copy and flags those specific gaps. An AI chatbot or assistant with no disclosure next to it. AI-generated media with no visible label and no accessible disclosure. AI-origin ad or marketing copy with no disclosure line. Sponsored or affiliate content with no material-connection language. And disclosure wording that technically exists but is too vague or buried to count.

    Each finding tells you what it is, why it matters in concrete terms, and the plain fix. It reads your source and text only. It does not run your app, touch the network, or read secrets. The rules for FTC, US state, and ad-platform expectations live in an editable file you keep current, which is what keeps this useful as the rules keep moving.

    This is deliberately US and ad-platform focused (FTC, US state law, and Google, Meta, and TikTok ad policy). It is not an EU AI Act tool, and it pairs naturally with an ad-copy policy check.

    Use it when you want to know if your app or ads disclose AI the way US regulators and platforms expect, or check whether you are FTC compliant on AI content before you publish.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Heuristic. It flags missing or weak disclosure signals for you to review. It is US and ad-platform focused, not an EU AI Act tool, and it is not legal advice. The machine-readable-label and vague-wording checks are advisory. The rules are only as current as the editable disclosure-rules.json you maintain. It reads code and text, not rendered pages, and it does not run your app.

    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 buying a skill.

    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 4 months ago

    Permissions

    Read Files

    File Scopes

    **/*.html
    **/*.jsx
    **/*.tsx
    **/*.js
    **/*.ts
    **/*.md
    **/*.txt
    **/*.json

    Read Files only. It reads your source and copy as plain text to find missing disclosure signals. It does not run the app, read your live environment, use secrets, or send anything anywhere. No write, no shell, no network.

    Listed4 months ago

    What's inside

    Frequently Asked Questions

    This skill audits your application code, website text, and advertisement copy to identify missing AI disclosures required by the FTC, state laws, and major ad platforms like Google, Meta, and TikTok.

    The skill acts as a read-only auditor that scans your source files and copy for undisclosed chatbots, unlabeled AI media, and missing material-connection language in sponsored content.

    It is specifically optimized for US-based regulatory environments (FTC/State) and private ad platform policies; it is not designed to audit for the EU AI Act or international frameworks.

    Since disclosure requirements change frequently, the skill utilizes an editable rules file that allows you to update specific FTC or platform mandates as they evolve.

    The Linter is a read-only tool that analyzes text and code patterns; it does not execute your code, access external networks, or interact with your private environment secrets.

    This skill is designed for compatibility with most standard AI agents capable of file analysis and text processing, making it an ideal addition to your existing frontend audit or marketing-tech workflow.

    New in Security