.claude/skills/v3-security-overhaul/SKILL.md
Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 implementation.
npx skillsauth add softmg/product-tracker V3 Security OverhaulInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Orchestrates comprehensive security overhaul for claude-flow v3, addressing critical vulnerabilities and establishing security-first development practices using specialized v3 security agents.
# Initialize V3 security domain (parallel)
Task("Security architecture", "Design v3 threat model and security boundaries", "v3-security-architect")
Task("CVE remediation", "Fix CVE-1, CVE-2, CVE-3 critical vulnerabilities", "security-auditor")
Task("Security testing", "Implement TDD London School security framework", "test-architect")
npm update @anthropic-ai/claude-code@^2.0.31
npm audit --audit-level high
// ❌ Old: SHA-256 with hardcoded salt
const hash = crypto.createHash('sha256').update(password + salt).digest('hex');
// ✅ New: bcrypt with 12 rounds
import bcrypt from 'bcrypt';
const hash = await bcrypt.hash(password, 12);
// ✅ Generate secure random credentials
const apiKey = crypto.randomBytes(32).toString('hex');
import { z } from 'zod';
const TaskSchema = z.object({
taskId: z.string().uuid(),
content: z.string().max(10000),
agentType: z.enum(['security', 'core', 'integration'])
});
function securePath(userPath: string, allowedPrefix: string): string {
const resolved = path.resolve(allowedPrefix, userPath);
if (!resolved.startsWith(path.resolve(allowedPrefix))) {
throw new SecurityError('Path traversal detected');
}
return resolved;
}
import { execFile } from 'child_process';
// ✅ Safe: No shell interpretation
const { stdout } = await execFile('git', [userInput], { shell: false });
documentation
Task tracking and plan management. Used by planner to create plans and persist tasks, by orchestrator to read tasks and update progress, by documenter to create completion reports, and by any agent to log non-critical issues.
development
Create, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an existing skill, running evals to test a skill, benchmarking skill performance, optimizing a skill's description for better triggering, reviewing third-party skills for quality, or packaging skills for distribution. Not for using skills or general coding tasks.
development
Simple implementation workflow - code, test, document. Use when user invokes /implement, wants to create code with automatic testing and documentation, or for simple single-purpose tasks that don't need planning.
development
Security best practices covering authentication, input validation, API security, secrets management, data protection, and OWASP Top 10. Use when implementing auth flows, API endpoints, file uploads, or any feature touching passwords, tokens, PII, or sensitive data. Do NOT use for code style reviews or architecture decisions.