Orchestration Security Reviewer — Security agent for Claude Code
Independent security gate for a PR.
How to install Orchestration Security Reviewer
Installs to ~/.claude/agents/dusttoo-claude-orchestrator-orchestration-security-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Dusttoo/claude-orchestrator/HEAD/agents/orchestration-security-reviewer.md -o ~/.claude/agents/dusttoo-claude-orchestrator-orchestration-security-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Orchestration Security Reviewer does
name: orchestration-security-reviewer description: Independent security gate for a PR. A separate agent from the code reviewer, hunting only for data leaks, privilege escalation, and isolation/authorization breaks. Returns concise structured findings. Use as the third stage when the change touches auth, data isolation, migrations, or payments.
You are the security gate. Code quality is someone else's gate; yours is "can this PR leak data, escalate privilege, break isolation, or expose a
Alternatives in Security
- Perf Deep Audit — Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially f 358 ★
- Offensive Security Engineer — Red-team the verification engine 179 ★
- Rust-claude-code-api V0.6.0 Quality Audit Report — Date: 2026-02-11 Auditors: Claude Code (team lead) + Codex (security) + Gemini CLI (API ergonomics) Method: 3 152 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cloud Security
Delegates to this agent when the user asks about cloud security testing, AWS/Azure/GCP penetration testing, cl
Redteam Agent
Red Team penetration testing agent for HTB Expressway. Use when the user wants to attack or pentest the target
Sec Arch
Security-focused L2+ specialist for authn/authz, trust boundaries, privilege escalation, and dangerous API/sec
Ad Security Reviewer
Use this agent when you need to audit Active Directory security posture, evaluate privilege escalation risks,
LLM Sec Review
LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode
Fact Reviewer
Independent fact-checker for completed analysis pipelines. Use when an analysis (model + structured output + f
Related Skills
Auth Audit
Full auth & session audit: login flow, session/cookie security, JWT handling, middleware safety, privilege esc
Privilege Escalation Triage
Decide whether an observed privilege change (setuid/ptrace/capability) is a real escalation attempt or benign.
Skill Auditor Desktop
Security audit skill for claude.ai / Claude Desktop — scans uploaded skills for prompt injection, data exfiltr