Works with the AI Agents you already use
Security Headers CSP Auditor
Audit HTTP security headers and CSP strings for misconfigurations, weak values, and dangerous CORS patterns.
$1
Security Headers CSP Auditor
Example session with this skill installed
I just ran curl -I on my site and got these headers. Is this CSP actually protecting me or is it just fluff? [pasted headers containing CSP with unsafe-inline and missing HttpOnly on cookies]
- Read your context and instructions
- Compiled the security headers csp
Your CSP is currently ineffective against XSS because it includes 'unsafe-inline' in script-src. I recommend implementing a nonce-based policy. Also, your session cookie lacks the HttpOnly flag, meaning a successful XSS could steal the session token. Fix these two first.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Security headers are often present but misconfigured, providing a false sense of security while leaving sites vulnerable to XSS, clickjacking, and session hijacking. Manually auditing complex CSP strings and CORS configurations is error-prone and time-consuming.
What it does
- Analyzes raw HTTP response headers for missing or weak security configurations.
- Performs deep directive-by-directive audits of Content-Security-Policy (CSP) to flag bypasses like
unsafe-inlineor over-broad wildcards. - Identifies dangerous CORS patterns, specifically the origin-reflection plus credentials trap.
- Audits
Set-Cookieflags for session protection, includingHttpOnly,Secure, andSameSite. - Prioritizes findings based on exploitability, moving beyond simple presence-checks to evaluate actual value effectiveness.
Why this beats prompting it yourself
General-purpose LLMs often report a header as "safe" just because the key exists. This skill uses specific logic to detect subtle CSP bypasses and invalid CORS combinations that standard prompts miss. It provides exact syntax for nonce-based or hash-based remediations rather than generic advice.
Use cases
- Auditing a production site by pasting raw headers from browser DevTools.
- Hardening CSP for an application that currently uses
unsafe-inline. - Verifying session cookie security flags during a security review.
- Debugging CORS errors that might be masking serious misconfigurations.
Known limitations
Requires raw header data or curl output to be provided by the user, as it cannot directly fetch headers from a URL. Focused on HTTP response-level security, not application-layer logic vulnerabilities.
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 raw header data or curl output as input. Focused on HTTP response headers, not application-level logic flaws.
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 2 months ago
Permissions
Allowed Hosts