Security Audit logo

Security Audit

Community
neuromechanist
security-audit

This skill should be used when the user says "security audit", "check for vulnerabilities", "security review", "harden project", "dependency audit", "credential scan", "check for secrets", "scan for secrets", "OWASP review", "security checklist", "audit dependencies", "find vulnerabilities", or wants to review their project for security issues, exposed credentials, or vulnerable dependencies.

Overview

Publisherneuromechanist
Repositoryresearch-skills
Skill namesecurity-audit
Stars
51
Forks
9
Bundled files
2
LicenseBSD-3-Clause
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by neuromechanist on GitHub. Read the source before you install it.

Installation

Install the Security Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/neuromechanist/research-skills/tree/main/plugins/project/skills/security-audit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/neuromechanist/research-skills.git /tmp/research-skills
mkdir -p .claude/skills
cp -r /tmp/research-skills/plugins/project/skills/security-audit .claude/skills/security-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Security Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Security Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Security Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Security Audit

Systematic security review of a project covering dependency vulnerabilities, credential exposure, common code vulnerabilities, and configuration hardening.

When to Use

  • Before a release or deployment
  • After adding new dependencies
  • When onboarding to a new codebase
  • Periodic security reviews
  • After receiving a vulnerability report

Audit Checklist

1. Credential and Secret Scanning

Check for exposed secrets in the codebase:

bash
# Check for common secret patterns in tracked files
git grep -n -i -E '(api_key|apikey|secret|password|token|credential|private_key)\s*[:=]' -- ':!*.md' ':!*.lock'

# Check for .env files tracked in git
git ls-files | grep -i '\.env'

# Check .gitignore covers sensitive files
for f in .env .env.local credentials.json secrets.yaml; do
  git check-ignore "$f" 2>/dev/null || echo "WARNING: $f not in .gitignore"
done

Files that must never be committed:

  • .env, .env.* (environment variables)
  • credentials.json, service-account.json (cloud credentials)
  • *.pem, *.key (private keys)
  • *.p12, *.pfx (certificates with private keys)

2. Dependency Vulnerability Scan

Python:

bash
uv run pip-audit

JavaScript/TypeScript:

bash
bun pm audit
# or check with npm for broader database
npm audit --omit=dev

Go:

bash
govulncheck ./...

Review results against the severity rubric (shared with the dependency-auditor agent):

  • Critical: exploitable now or actively exploited (leaked live credential, known-exploited CVE in a reachable path). Must fix before release; blocks release-prep.
  • High: known vulnerability with a plausible attack path. Fix before the next release.
  • Medium: vulnerability with mitigating factors, or a major-version lag on a security-relevant package. Fix within the sprint.
  • Low: outdated without known vulnerabilities; license concerns to review. Track in backlog.

3. Code Vulnerability Patterns

Scan for common vulnerability patterns:

SQL Injection:

bash
# Look for string interpolation in SQL
grep -rn 'f".*SELECT\|f".*INSERT\|f".*UPDATE\|f".*DELETE' --include='*.py'
grep -rn "format.*SELECT\|format.*INSERT" --include='*.py'

Command Injection:

bash
# Look for shell=True or unsanitized subprocess calls
grep -rn 'shell=True\|os\.system\|subprocess\.call.*shell' --include='*.py'
grep -rn 'exec(\|eval(' --include='*.py' --include='*.js' --include='*.ts'

XSS (Cross-Site Scripting):

bash
# Look for dangerouslySetInnerHTML or unescaped output
grep -rn 'dangerouslySetInnerHTML\|innerHTML\s*=' --include='*.tsx' --include='*.jsx' --include='*.ts' --include='*.js'

Path Traversal:

bash
grep -rn 'open(.*\+\|os\.path\.join.*input\|req\.\(params\|query\|body\)' --include='*.py' --include='*.js'

4. Authentication and Authorization

Review:

  • Authentication endpoints use constant-time comparison for secrets
  • Session tokens have appropriate expiration
  • CORS configuration is restrictive (not * in production)
  • Rate limiting on auth endpoints
  • Password hashing uses bcrypt/argon2 (not MD5/SHA1)

5. Configuration Hardening

  • Debug mode disabled in production configs
  • HTTPS enforced (HSTS headers)
  • Security headers present (CSP, X-Frame-Options, X-Content-Type-Options)
  • Error messages do not leak stack traces in production
  • Logging does not include sensitive data (passwords, tokens)

6. Docker Security (if applicable)

  • Non-root user in Dockerfile
  • Base image is pinned to specific version (not latest)
  • No secrets in Docker build args or layers
  • Health checks configured
  • Read-only filesystem where possible

7. CI/CD Security

  • Secrets stored in GitHub Secrets (not in workflow files)
  • Third-party actions pinned to SHA (not tags)
  • Minimal permissions in workflow permissions: block
  • No pull_request_target with actions/checkout of PR head

Output Format

Present findings as a prioritized list:

## Security Audit Results

### Critical (must fix)
1. [CRED] API key found in src/config.py:42 - move to environment variable
2. [DEP] lodash 4.17.20 has prototype pollution (CVE-2021-23337)

### High (fix before release)
3. [CODE] SQL injection risk in src/db.py:88 - use parameterized queries

### Medium (fix within sprint)
4. [CONFIG] CORS allows * origin in production config

### Low (backlog)
5. [STYLE] Error responses include stack traces in non-debug mode

### Passed
- [x] No .env files in git
- [x] Docker runs as non-root
- [x] Dependencies up to date

Additional Resources

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Security Audit AI skill do?

This skill should be used when the user says "security audit", "check for vulnerabilities", "security review", "harden project", "dependency audit", "credential scan", "check for secrets", "scan for secrets", "OWASP review", "security checklist", "audit dependencies", "find vulnerabilities", or wants to review their project for security issues, exposed credentials, or vulnerable dependencies.

Why use Security Audit on TypingMind?

Because you install it once and use it with any model. Security Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Security Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/neuromechanist/research-skills/tree/main/plugins/project/skills/security-audit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Security Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Security Audit?

As many as you like. As long as a model supports skills, you can use Security Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Security Audit AI skill free?

Yes. It is published on GitHub by neuromechanist under the BSD-3-Clause license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇