Works with the AI Agents you already use
Browser Extension Auditor
Audit browser extensions for security risks and generate MDM-ready allowlist/blocklist policies.
$1
Browser Extension Auditor
Example session with this skill installed
Analyze the 5 CSV files in ./audit_data/ against my allowlist in safe_exts.txt. Flag anything with 'all_urls' permissions and generate Chrome/Edge policy files.
- Read your context and instructions
- Compiled the browser extension auditor
I have processed the extension data from 5 machines (host-pc-01, host-pc-02, host-pc-03, mbp-dev-12, work-station-09). The analysis identified 14 unique extensions, 3 of which possess high-risk permissions not present on your allowlist.
Extension Audit Results
| Extension Name | ID | Risk Level | Permission Flags | Count |
|---|---|---|---|---|
| Unverified Adblocker | gighmmpiobklfepjocnamgkkbiglidgl | HIGH | <all_urls>, webRequest, tabs | 2 |
| Legacy Script Tool | pkecljijimconemakjednondbacoccej | MEDIUM | Manifest V2, storage | 1 |
| Approved Password Manager | nmgpnhpnlnuficbbjehihxkudskednnt | LOW | allowlisted | 5 |
| Random Weather Tab | jbkickhgoadomhlchoocnabaaknikbom | HIGH | <all_urls>, cookies, clipboard | 1 |
Generated Policy Configuration (Chrome/Edge)
{
"ExtensionSettings": {
"*": {
"installation_mode": "blocked"
},
"nmgpnhpnlnuficbbjehihxkudskednnt": {
"installation_mode": "force_installed",
"update_url": "https://clients2.google.com/service/update2/crx"
}
},
"ExtensionInstallAllowlist": [
"nmgpnhpnlnuficbbjehihxkudskednnt"
],
"ExtensionInstallBlocklist": [
"gighmmpiobklfepjocnamgkkbiglidgl",
"jbkickhgoadomhlchoocnabaaknikbom"
]
}
Next steps
- Review the
policies/firefox_settings.jsonfile for Firefox-specific deployments. - Validate the
ExtensionSettingsJSON in a test Organizational Unit (OU) before global deployment. - Investigate
work-station-09regarding the high-risk 'Random Weather Tab' installation.
Connects securely to your tools. The creator never sees your data.
About this skill
Browser extensions often bypass perimeter security by reading sensitive cookies, intercepting web requests, or scraping clipboard data. This skill identifies high-risk extensions across your fleet and generates the configuration files needed to enforce a lock-down policy.
What it does
- Multi-browser discovery extracts installed extensions from Chrome, Edge, Brave, and Firefox profiles.
- Permission analysis flags extensions that can read all website data, access browsing history, or use native messaging.
- Shadow IT detection highlights rare or unique extensions installed by single users that may bypass corporate standards.
- Version auditing identifies Manifest V2 extensions nearing end-of-life to prevent workflow disruption.
- Policy generation outputs ready-to-deploy JSON for Chrome, Edge, and Firefox management.
How it works
- Run the collection script on target machines or via RMM to generate CSV profile data.
- Aggregate CSV files into a central directory for cross-machine analysis.
- Execute the audit script with optional allowlists and blocklists to categorize findings.
- Review the generated policy files in the output directory.
Frameworks & tools
Python 3 scripts for data collection and analysis. Outputs standard JSON policy formats compatible with Group Policy (GPO), Microsoft Intune, and various MDM platforms.
Why this beats prompting it yourself
Generic LLMs cannot access local filesystem paths to parse SQLite or JSON browser profiles directly. This skill provides the specific logic needed to resolve localized folder names and map raw permission strings to actual security risks.
Use cases
- Auditing the fleet after a data breach involving a malicious browser add-on.
- Building a baseline extension allowlist for a new SOC 2 compliance initiative.
- Identifying and removing deprecated Manifest V2 extensions before browser updates break them.
- Monitoring for unauthorized "shadow IT" tools installed by employees.
Known limitations
Scripts must be executed locally on target machines or deployed via RMM. Localized profile names are supported, but custom non-standard install paths may require manual configuration.
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.
Requires Python 3. Must run collection scripts locally or via RMM on target machines. Limited to Chrome, Edge, Brave, and Firefox profiles on standard OS paths.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 1 month ago