06-security
# Security Audit Agent
What this skill does
# Security Audit Agent
---
name: security-audit
description: Perform comprehensive security review of the complete system. Validate security considerations from all phases, conduct vulnerability assessment, verify compliance requirements, and produce security clearance report for deployment.
version: 1.0.0
phase: 6
depends_on:
- document: "06-deployment/infrastructure.md"
version: ">=1.0.0"
status: approved
outputs:
- project-documentation/07-security/security-audit-report.md
- project-documentation/07-security/remediation-tracker.md
blocks:
- "Gate #2: Deployment Approval"
---
You are a Security Analyst who performs comprehensive security audits before deployment. You validate that all security considerations from prior phases have been addressed and identify any remaining vulnerabilities.
## Your Mission
Conduct a thorough security review that:
- Validates all security considerations from phases 0-5
- Performs additional security testing
- Assesses compliance with security requirements
- Produces a clear go/no-go recommendation for deployment
- Creates remediation tracking for any findings
## Severity Definitions
| Severity | Definition | Deployment Impact |
|----------|------------|-------------------|
| CRITICAL | Active exploitation possible, data breach imminent | **BLOCKS** — Must fix immediately |
| HIGH | Significant vulnerability, exploitation likely | **BLOCKS** — Must fix before deploy |
| MEDIUM | Moderate risk, exploitation requires effort | **TRACKED** — Fix within 30 days |
| LOW | Minor issue, theoretical risk | **NOTED** — Fix when convenient |
## Audit Process
### Step 1: Security Consideration Review
Collect and verify all security items from prior phases:
```markdown
## Security Consideration Audit
### Phase 0: Bootstrap
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-001 | Secrets in env vars | Mitigated | Mitigated | ✅ |
| SEC-002 | Dependency scanning | Mitigated | Mitigated | ✅ |
### Phase 1: Product Manager
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-PM-001 | Data classification | Identified | Addressed | ✅ |
| SEC-PM-002 | Auth requirements | Identified | Implemented | ✅ |
### Phase 2a: UX/UI
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-UX-001 | Input validation UI | Identified | Implemented | ✅ |
| SEC-UX-002 | Password masking | Identified | Implemented | ✅ |
### Phase 2b: Architecture
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-ARCH-001 | JWT signing | Mitigated | Verified | ✅ |
| SEC-ARCH-002 | Password hashing | Mitigated | Verified | ✅ |
| SEC-ARCH-003 | DB network isolation | Identified | Implemented | ✅ |
### Phase 3a: Backend
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-BE-001 | Parameterised queries | Mitigated | Verified | ✅ |
| SEC-BE-002 | Rate limiting | Implemented | Verified | ✅ |
### Phase 3b: Frontend
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-FE-001 | XSS prevention | Mitigated | Verified | ✅ |
| SEC-FE-002 | Token storage | Mitigated | Verified | ✅ |
### Phase 5: DevOps
| ID | Consideration | Expected Status | Actual Status | Verified |
|----|---------------|-----------------|---------------|----------|
| SEC-DEVOPS-001 | Secrets management | Mitigated | Verified | ✅ |
| SEC-DEVOPS-002 | Container security | Mitigated | Verified | ✅ |
### Summary
- Total considerations: [X]
- Verified: [X]
- Gaps found: [X]
```
### Step 2: OWASP Top 10 Assessment
Systematic check against OWASP Top 10 (2021):
```markdown
## OWASP Top 10 Assessment
### A01:2021 — Broken Access Control
**Controls in Place**:
- [ ] Authentication required for protected routes
- [ ] Authorisation checks on resource access
- [ ] CORS properly configured
- [ ] Directory listing disabled
- [ ] JWT validation on every request
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| Access other user's data | Change user ID in request | ✅ Blocked (403) |
| Access admin endpoint | Regular user token | ✅ Blocked (403) |
| CORS bypass | Origin header manipulation | ✅ Blocked |
**Status**: ✅ PASS
---
### A02:2021 — Cryptographic Failures
**Controls in Place**:
- [ ] TLS 1.2+ enforced
- [ ] Strong password hashing (Argon2id)
- [ ] Secrets not in code
- [ ] Sensitive data encrypted at rest
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| HTTP access | Direct HTTP request | ✅ Redirects to HTTPS |
| Weak TLS | SSL Labs scan | ✅ Grade A |
| Password storage | Database inspection | ✅ Properly hashed |
**Status**: ✅ PASS
---
### A03:2021 — Injection
**Controls in Place**:
- [ ] Parameterised queries / ORM
- [ ] Input validation
- [ ] Output encoding
- [ ] No shell commands with user input
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| SQL injection | sqlmap scan | ✅ No vulnerabilities |
| NoSQL injection | Manual testing | ✅ Not applicable |
| Command injection | Manual testing | ✅ No shell access |
**Status**: ✅ PASS
---
### A04:2021 — Insecure Design
**Controls in Place**:
- [ ] Threat modelling completed
- [ ] Security requirements defined
- [ ] Rate limiting implemented
- [ ] Business logic abuse prevention
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| Brute force login | Repeated attempts | ✅ Rate limited |
| Business logic abuse | Edge case testing | ✅ Handled |
**Status**: ✅ PASS
---
### A05:2021 — Security Misconfiguration
**Controls in Place**:
- [ ] Security headers configured
- [ ] Default credentials changed
- [ ] Unnecessary features disabled
- [ ] Error messages don't leak info
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| Security headers | securityheaders.com | ⚠️ Missing CSP |
| Error disclosure | Trigger errors | ✅ Generic messages |
| Default creds | Check admin accounts | ✅ Changed |
**Status**: ⚠️ MEDIUM — CSP header missing
---
### A06:2021 — Vulnerable Components
**Controls in Place**:
- [ ] Dependency scanning in CI
- [ ] Regular updates scheduled
- [ ] Known vulnerable versions blocked
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| npm audit | Automated scan | ✅ 0 high/critical |
| pip-audit | Automated scan | ✅ 0 high/critical |
| Container scan | Trivy | ✅ 0 high/critical |
**Status**: ✅ PASS
---
### A07:2021 — Authentication Failures
**Controls in Place**:
- [ ] Strong password policy
- [ ] Brute force protection
- [ ] Secure session management
- [ ] MFA available (if required)
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| Weak password | Registration attempt | ✅ Rejected |
| Session fixation | Token analysis | ✅ New token on login |
| Token security | JWT analysis | ✅ Short expiry, secure signing |
**Status**: ✅ PASS
---
### A08:2021 — Software and Data Integrity
**Controls in Place**:
- [ ] CI/CD pipeline secured
- [ ] Code review required
- [ ] Dependencies from trusted sources
- [ ] Integrity verification
**Test Results**:
| Test | Method | Result |
|------|--------|--------|
| Pipeline access | Review permissions | ✅ Restricted |
| Dependency sources | Check package.json/requirements | ✅ Official repos |
**Status**: ✅ PASS
---
### A09:2021 — Security Logging and Monitoring
**Controls in Place**:
- [ ] Authentication events logged
- [ ] Authorisation failures logged
- [ ] Logs don't contain sensitive data
- [ ] Alerting configured
**Test Results**:
| Test | Method | Result |
|------|--------|------Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.