Works with the AI Agents you already use
Security Headers Audit
Produces a legal-markdown report with the top 3 corrections, ready to hand to a client.
Free
Security Headers Audit
Example session with this skill installed
Audit the security headers for https://searching-murphy.com and tell me the score and what I need to fix first.
- Read your context and instructions
- Compiled the security headers audit
I have performed a passive security header audit for https://searching-murphy.com. The site scored 87/100.
Security Header Audit Report
Target: https://searching-murphy.com
Scan Date: 2026-10-12
Overall Security Score: 87/100
| Header | Status | Points |
|---|---|---|
| Content-Security-Policy | OK (weak) | 12/25 |
| Strict-Transport-Security | OK | 20/20 |
| X-Frame-Options | OK | 15/15 |
| X-Content-Type-Options | OK | 15/15 |
| Referrer-Policy | OK | 15/15 |
| Permissions-Policy | OK | 10/10 |
Before / After - real progression
This is a real measurement, taken by the tool itself on the same URL.
Before - no headers configured:
Time spent: under 2 hours. Remediation: 6 lines in .htaccess.
Priority Remediation Steps
Content-Security-Policy - the only remaining weakness. script-src uses 'unsafe-inline' without nonce or hash. This is common on WordPress (Astra theme + plugins require it). A proper fix needs a CSP with nonce - the exact directives are documented in references/headers-explained.md.
An honest note on scores
87/100 on WordPress is in the high range. A perfectly configured site caps around 90/100 - the last points depend on technical choices (CSP nonce/hash) and server configuration, not just header presence.
Legal Disclaimer: This report is for informational purposes only. A high score does not guarantee total security. Always perform comprehensive penetration testing.
Next steps
- Copy the recommended CSP directives into your web server configuration (Nginx / Apache).
- Verify HSTS settings in a staging environment before pushing to production - a misconfigured HSTS can lock visitors out.
- Re-run this audit after deployment to confirm the score increase.
Connects securely to your tools. The creator never sees your data.
About this skill
Insecure HTTP headers leave web applications vulnerable to clickjacking, XSS, and protocol downgrades. This skill audits a target URL for six critical security headers, providing an immediate risk score and prioritized remediation steps.
Tested on a real WordPress site: searching-murphy.com went from 0/100 to 87/100 in under 2 hours using the exact remediation steps documented in this skill. The full before/after report is in the demo section.
What it does
- Header inspection identifies presence and configuration of CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, and Permissions-Policy.
- Weighted scoring calculates a security posture rating out of 100 based on header importance.
- Risk prioritization highlights the top three missing or misconfigured headers that require urgent attention.
- Reporting generates a Markdown-formatted report including legal disclaimers and technical findings.
How it works
- Run the audit script by providing a target HTTP or HTTPS URL.
- The tool performs a single non-aggressive GET request with a dedicated User-Agent.
- Review the terminal output or the generated Markdown file for the score and remediation priorities.
Frameworks & tools
This skill runs on Python 3.8+ using the standard library. It requires no external dependencies, API keys, or cloud services.
Why this beats prompting it yourself
Manual inspection of network tabs is slow and prone to overlooking specific directive errors. This skill uses a weighted rubric to quantify security risk and provides a consistent, professional report format that is ready for client delivery or internal documentation.
Use cases
- Auditing new production deployments for basic security hardening.
- Running quick competitive benchmarks on site security posture.
- Generating security compliance artifacts for internal documentation.
Known limitations
Does not perform active vulnerability scans or payload injections. It cannot bypass WAFs that block the specific User-Agent or private IP ranges.
Restricted to public URLs only; private IP ranges and localhost are blocked. Performs passive analysis only and does not apply automatic fixes to the server configuration.
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 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
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts