Owasp Top10 Reviewer
A rigorous security auditor that scans code for OWASP Top 10 vulnerabilities with severity ratings and concrete fixes.
$15
Works with the AI Agents you already use
owasp-top10-reviewer
Example session with this skill installed
@app.route("/user/<user_id>/profile")
def get_profile(user_id):
query = f"SELECT * FROM users WHERE id = {user_id}"
result = db.execute(query)
return jsonify(result)
- Read your context and instructions
- Compiled the owasp-top10-reviewer
OWASP Top 10 Security Audit Report
Scope: get_profile endpoint — app.py
Language/Framework: Python + Flask
Risk Summary: 0 Critical 2 High 1 Medium 0 Low
A01: Broken Access Control — FAIL
Finding: No authentication check. Any user can access any other user's profile
by changing the user_id parameter (IDOR).
Severity: High
Fix: Add session/JWT check. Verify current_user.id == user_id before executing query.
A02: Cryptographic Failures — PASS
Finding: No issues found in this snippet.
A03: Injection — FAIL
Finding: f-string interpolation directly in SQL query. Passing user_id=1 OR 1=1
dumps the entire users table.
Severity: High
Fix: db.execute("SELECT * FROM users WHERE id = ?", (user_id,))
A04: Insecure Design — PASS
A05: Security Misconfiguration — FAIL
Finding: jsonify(result) returns all columns including password hashes.
Severity: Medium
Fix: SELECT id, name, email FROM users WHERE id = ?
A06–A10: PASS or N/A (not applicable to this endpoint snippet)
Overall Assessment
Two High-severity vulnerabilities allow any unauthenticated user to read or dump
the entire users table. Fix A03 first — it is trivial to exploit with one request.
Immediate Actions
- Replace f-string SQL with parameterized query (A03 — High)
- Add authentication + IDOR check (A01 — High)
- Restrict SELECT to needed columns (A05 — Medium)
Connects securely to your tools. The creator never sees your data.
About this skill
Automated OWASP Top 10 Security Auditing
Ensure your applications are secure before they ever hit production. This skill performs a rigorous, deep-dive security audit of your source code, API endpoints, and system designs, specifically checking against the 2021 OWASP Top 10 vulnerabilities.
What it does
It acts as an automated security architect that reviews your pull requests or snippets for risks like SQL injection, broken access control, and cryptographic failures. Unlike general-purpose LLM prompting, this skill follows a strict 10-point inspection protocol, ensuring no category is overlooked and every finding is backed by a concrete fix.
- Comprehensive Coverage: Systematic checks from A01 (Access Control) to A10 (SSRF).
- Development Framework Support: Expert analysis for Node.js, Python, Java, Go, and more.
- Context-Aware Ratings: Issues are categorized by severity (Critical to Low) based on real-world exploitability.
- Actionable Remediation: Every vulnerability includes the specific code change required to fix it.
Why use this skill
While standard AI might catch obvious bugs, this skill is programmed with a security-first mindset. It identifies structural design flaws, insecure configurations, and dependency risks that simple code reviews miss. The output is a professional, structured audit report ready for developers and stakeholders alike.
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.
Reviews the provided code only — cannot assess backend infrastructure, dependencies, or services not shown. Scope is always stated explicitly at the top of every report. Does not replace a professional security audit for compliance-critical systems.
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 6 months ago
- Software
Python