Security Guidance
Checks every file edit and commit for security holes before they happen, mapping issues to OWASP and enterprise security frameworks.
Before & after
Same prompt, same agent — the only difference is the skill.
I can review your code for security issues. There are a lot of common vulnerabilities to watch out for — SQL injection, cross-site scripting, authentication problems, data exposure, that kind of thing. I'd need to see the actual code changes to identify specific risks. It would help to know what framework you're using, what databases you're connecting to, and how you're handling authentication. Different types of vulnerabilities need different fixes. I could flag issues and suggest improvements, but you'd probably want to have security expertise on your team review anything critical before it goes live. Do you want me to focus on a particular part of your code or look at the full diff?
PRE-DEPLOYMENT SECURITY SCAN
OWASP A03:2021 — INJECTION (CRITICAL)
File: api/search.ts, Line 42
Vulnerability: User input passed directly to database query
const results = db.query("SELECT * FROM posts WHERE tags LIKE '" + userInput + "'")
Risk: Attacker input "'; DROP TABLE posts; --" destroys data
Fix: Use parameterized queries
db.query("SELECT * FROM posts WHERE tags LIKE ?", userInputParam)
Impact: Critical — stop deployment until fixed
OWASP A01:2021 — BROKEN ACCESS CONTROL (HIGH)
File: api/user-admin.ts, Line 67
Vulnerability: Admin check missing on endpoint
app.delete("/user/:id", (req, res) => { /* no role check */ })
Risk: Any user can delete any other user
Fix: Add auth middleware
app.delete("/user/:id", requireAdmin, (req, res) => { ... })
Impact: High — review before deploy
OWASP A02:2021 — CRYPTOGRAPHIC FAILURE (MEDIUM)
File: auth.ts, Line 15
Issue: Passwords hashed with MD5 (weak, rainbow-table vulnerable)
Fix: Use bcrypt or argon2
const hash = await bcrypt.hash(password, 12)
Impact: Medium — scheduled for next sprint
REPORT: 1 Critical, 1 High, 1 Medium found. Deploy blocked until Critical resolved.About this skill
name: security-guidance description: Use when Checks every file edit and commit for security holes before they happen, mapping issues to OWASP and enterprise security frameworks.
Security Guidance
Security Guidance runs a real-time security review on every action Claude takes. It monitors file edits, commits, and tool calls for vulnerabilities before they execute, mapping findings to OWASP and other enterprise frameworks used by billion-dollar software companies. Enterprises now treat this as mandatory, not optional.
What you get
- Pre-execution security scanning, OWASP-mapped vulnerability reports, risky operation flags before code runs, enterprise-grade security coverage for autonomous Claude sessions.
Customize your output
- Pair with Semgrep skills for deeper security reviews. Configure which frameworks to check against (OWASP, SANS, custom).
Example output
Security report: SQL injection risk flagged at database query line 42, mapped to OWASP A03:2021 — Injection. Fix suggested before execution.
Best for
Developers, vibe coders, and enterprises deploying autonomous Claude agents who need security coverage baked into every session.
SKILL.md preview
---
name: security-guidance
description: Use this skill on every file edit, commit, or tool call to run a real-time security review that maps findings to OWASP and other enterprise security frameworks before code ships.
version: 1.0.0
category: Security / Development
author: AgentVolt
license: proprietary
tags:
- security
- development
- standard
---
# Security Guidance
Runs a continuous security review on code changes as they happen, catching vulnerabilities before commit and mapping findings to the relevant OWASP or enterprise control.
## When to use
… (sign up to view the full skill)