Gravitas Security logo

Gravitas Security

Community
udaysharmadev
gravitas-security

Deep security review mode for GRAVITAS. Adds threat modeling, OWASP Top 10 checks, injection prevention patterns, auth/session security, and security-specific test requirements. Load for any auth, input handling, database, or API work.

Overview

Publisherudaysharmadev
RepositoryGravitas
Skill namegravitas-security
Stars
312
Forks
29
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Gravitas Security 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/udaysharmadev/Gravitas/tree/main/plugins/gravitas-security
  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/udaysharmadev/Gravitas.git /tmp/Gravitas
mkdir -p .claude/skills
cp -r /tmp/Gravitas/plugins/gravitas-security .claude/skills/gravitas-security
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gravitas Security 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 Gravitas Security 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 Gravitas Security 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.

GRAVITAS — Security Extension

Deep security review mode. Load in addition to skills/gravitas/SKILL.md. All security tasks are Tier 2 minimum. No exceptions.


Security Recon Additions

Beyond standard recon, always check:

bash
# SQL injection patterns
grep -rn "query.*\$\{" src/ --include="*.ts"
grep -rn "execute.*+.*req\." src/ --include="*.ts"
grep -rn "\.raw\|\.execute\|\.query" src/ --include="*.ts" | grep -v parameterized

# XSS patterns
grep -rn "innerHTML\|outerHTML\|document\.write\|insertAdjacentHTML" src/ --include="*.ts"
grep -rn "dangerouslySetInnerHTML" src/ --include="*.tsx"

# Hardcoded secrets
grep -rn "password\s*=\s*['\"]" src/ --include="*.ts"
grep -rn "api.key\s*=\s*['\"]" src/ --include="*.ts"
grep -rn "secret\s*=\s*['\"]" src/ --include="*.ts"
grep -rn "token\s*=\s*['\"]" src/ --include="*.ts"

# Auth bypass
grep -rn "skipAuth\|bypassAuth\|noAuth\|isAdmin.*=.*true" src/ --include="*.ts"

# Mass assignment
grep -rn "Object\.assign.*req\.body\|spread.*req\.body\|\.create(req\.body)" src/

# Insecure direct object reference
grep -rn "req\.params\.id\|req\.query\.id" src/ -A 3 | grep -v "userId.*session"

# Path traversal
grep -rn "readFile.*req\.\|__dirname.*req\." src/

OWASP Top 10 Checklist

For every security change, verify:

□ A01 Broken Access Control    — auth checked before data access
□ A02 Cryptographic Failures   — no plaintext passwords/secrets
□ A03 Injection                — parameterized queries everywhere
□ A04 Insecure Design          — threat model considered
□ A05 Security Misconfiguration— no debug mode in prod, no default creds
□ A06 Vulnerable Components    — no known-vulnerable dependencies
□ A07 Auth/Session Failures    — session invalidated on logout
□ A08 Software/Data Integrity  — dependencies verified, no eval()
□ A09 Security Logging         — auth failures logged, no PII in logs
□ A10 SSRF                     — no unvalidated URL fetching

Security Anti-Patterns

Injection (A03)

typescript
BAD:  db.query(`SELECT * FROM users WHERE id = ${req.params.id}`)
BAD:  db.query("SELECT * FROM users WHERE id = " + id)
GOOD: db.query('SELECT * FROM users WHERE id = $1', [id])

Broken Auth (A07)

typescript
BAD:  if (req.headers['x-admin'] === 'true') { grantAdmin(); }
BAD:  const user = { ...req.body, isAdmin: false }; // mass assignment — override possible
GOOD: const user = { username: req.body.username, email: req.body.email }; // explicit allowlist

Hardcoded Secrets (A02)

typescript
BAD:  const JWT_SECRET = 'mysecretkey123';
GOOD: const JWT_SECRET = process.env.JWT_SECRET;
      if (!JWT_SECRET) throw new Error('JWT_SECRET not set');

Missing Auth Check (A01)

typescript
BAD:  router.delete('/users/:id', async (req, res) => {
        await deleteUser(req.params.id); // no auth check!
      });
GOOD: router.delete('/users/:id', requireAuth, requireAdmin, async (req, res) => {
        await deleteUser(req.params.id);
      });

Required Security Tests

Every security fix must include tests that demonstrate the vulnerability is fixed:

typescript
describe('SQL injection prevention', () => {
  const payloads = [
    "'; DROP TABLE users; --",
    "' OR '1'='1",
    "' UNION SELECT password FROM admins --",
    "1; UPDATE users SET password = 'hacked'",
    "' OR 1=1 --",
  ];

  payloads.forEach(payload => {
    it(`blocks: ${payload.slice(0, 30)}...`, async () => {
      const result = await searchUsers(payload);
      expect(result).toEqual([]); // no data leaked, no crash
    });
  });
});

describe('Auth protection', () => {
  it('returns 401 on missing auth token', async () => {
    const res = await request(app).delete('/users/1');
    expect(res.status).toBe(401);
  });
  it('returns 403 on insufficient permissions', async () => {
    const res = await request(app)
      .delete('/users/1')
      .set('Authorization', `Bearer ${regularUserToken}`);
    expect(res.status).toBe(403);
  });
});

Security Verification Chain

bash
# Standard chain
tsc --noEmit && eslint . --max-warnings 0 && vitest run

# Security-specific grep checks
grep -rn "query.*\${" src/ --include="*.ts" | wc -l    # should be 0
grep -rn "innerHTML" src/ --include="*.ts" | wc -l     # should be 0
grep -rn "password.*['\"]" src/ --include="*.ts"       # should be 0

# Dependency audit
npm audit --audit-level=high                            # 0 high/critical

# Report
echo "Injection patterns: $(grep -rn "query.*\${"  src/ | wc -l) (want: 0)"
echo "XSS patterns:       $(grep -rn "innerHTML"    src/ | wc -l) (want: 0)"
echo "npm audit high:     $(npm audit --audit-level=high 2>&1 | grep 'found 0')"

VERDICT for Security Tasks

Security VERDICT requires ALL of:

  • Standard: tests pass, lint clean, types clean
  • Security: 0 injection patterns found
  • Security: security tests present and passing
  • Security: no new hardcoded secrets
  • Security: npm audit 0 high/critical
VERDICT: PASS (Security)

Tests:     47/47 (5 new security tests)
Lint:      clean
Types:     clean
Injection: 0 patterns found
Secrets:   0 hardcoded found
Audit:     0 high/critical vulnerabilities

Frequently asked questions

What does the Gravitas Security AI skill do?

Deep security review mode for GRAVITAS. Adds threat modeling, OWASP Top 10 checks, injection prevention patterns, auth/session security, and security-specific test requirements. Load for any auth, input handling, database, or API work.

Why use Gravitas Security on TypingMind?

Because you install it once and use it with any model. Gravitas Security 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 Gravitas Security in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/udaysharmadev/Gravitas/tree/main/plugins/gravitas-security. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gravitas Security?

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 Gravitas Security?

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

Is the Gravitas Security AI skill free?

Yes. It is published on GitHub by udaysharmadev under the MIT 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 👇