agentleFS
Sign inStart free
gologo13gologo13/agent-skills/skills/security-review/SKILL.md

security-review

Skill0 starsChanged 9 months agoMITView on GitHub

Perform a comprehensive security review of the current code and provide specific remediation...; keywords: security, api, review, error. Use only on explicit request; before execution, review diffs and list impact scope.

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify proper authentication mechanisms

    line 15
  2. Distinctive:

    Check authorization controls and permission systems

    line 16
  3. Distinctive:

    Ensure secure password policies and storage

    line 18
  4. Distinctive:

    Check for XSS and CSRF attack vectors

    line 21
  5. Distinctive:

    Ensure sensitive data encryption at rest and in transit

    line 25
  6. Distinctive:

    Check for data exposure in logs and error messages

    line 26
  7. Distinctive:

    Verify proper secrets management

    line 28
  8. Distinctive:

    Check HTTPS configuration and certificate validation

    line 31

“Common” is measured: kept by at least 6 in 10 of the 167 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Security Review

Overview

Perform a comprehensive security review of the current code and provide specific remediation steps with code examples for each security issue identified.

Steps

  1. Authentication & Authorization
    • Verify proper authentication mechanisms
    • Check authorization controls and permission systems
    • Review session management and token handling
    • Ensure secure password policies and storage
  2. Input Validation & Sanitization
    • Identify SQL injection vulnerabilities
    • Check for XSS and CSRF attack vectors
    • Validate all user inputs and API parameters
    • Review file upload and processing security
  3. Data Protection
    • Ensure sensitive data encryption at rest and in transit
    • Check for data exposure in logs and error messages
    • Review API responses for information leakage
    • Verify proper secrets management
  4. Infrastructure Security
    • Review dependency security and known vulnerabilities
    • Check HTTPS configuration and certificate validation
    • Analyze CORS policies and security headers
    • Review environment variable and configuration security

Security Review Checklist

  • Verified proper authentication mechanisms
  • Checked authorization controls and permission systems
  • Reviewed session management and token handling
  • Ensured secure password policies and storage
  • Identified SQL injection vulnerabilities
  • Checked for XSS and CSRF attack vectors
  • Validated all user inputs and API parameters
  • Ensured sensitive data encryption at rest and in transit
  • Checked for data exposure in logs and error messages
  • Reviewed dependency security and known vulnerabilities
  • Analyzed CORS policies and security headers

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free