Security Guidance

Checks every file edit and commit for security holes before they happen, mapping issues to OWASP and enterprise security frameworks.

Security / Developmentsecuritydevelopment
by AgentVoltv1.0.0Published 1y ago
Free to sign up · every skill included with AgentVolt Pro

Before & after

Same prompt, same agent — the only difference is the skill.

PromptI'm deploying code to prod tomorrow — catch any security issues in my changes.
Beforegeneric AI agent
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?
Afterwith Security Guidance
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

SKILL.md
---
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)
Sign up to view, copy, and install the full skill