Offensive Security Engineer — Security agent for Claude Code
Red-team the verification engine.
How to install Offensive Security Engineer
Installs to ~/.claude/agents/refactron-ai-refactron-offensive-security-engineer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Refactron-ai/refactron/HEAD/.claude/agents/offensive-security-engineer.md -o ~/.claude/agents/refactron-ai-refactron-offensive-security-engineer.md Restart Claude Code, or start a new session, for it to be picked up.
What Offensive Security Engineer does
name: offensive-security-engineer description: Red-team the verification engine. Use to hunt false SAFE verdicts, shadow-tree isolation escapes, credential leaks to the verified suite, and diff-intake abuses — by building working exploits against this repository, not by reading code and speculating. Complements security-engineer, which threat-models and reviews; this role attacks. tools: ['Bash', 'Read', 'Grep', 'Glob', 'WebFetch', 'WebSearch']
You are an offensive security engineer. Yo
Alternatives in Security
- Knowledge Base Loader — Phase KB0 intake agent that converts staged, untrusted application documentation into a cited, security-orient 125 ★
- Vuln Analyst — Use this agent to hunt for security vulnerabilities in a bounded region of the Revel codebase 107 ★
- SEO Audit — Analyze application for search engine optimization and discoverability 80 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Engine QA Review Security Governance
After a change you've asked for is built, checks whether it is safe to release — how it could be attacked or m
Deep Security Auditor
Adversarial red-team and security compliance specialist. Inspects ASTs for prompt injections, credential leaks
Code Reviewer Laravel
Use this agent when Laravel code needs a quality, security, or performance review — "review this PR", "audit t
Engineering Autonomous Optimization Architect
Intelligent system governor that continuously shadow-tests APIs for performance while enforcing strict financi
Autonomous Optimization Architect
Intelligent system governor that continuously shadow-tests APIs for performance while enforcing strict financi
Audit Reporter
Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity ro
Related Skills
T3mp3st
autonomous red teaming platform; multi-agent offensive-security meta-harness
Agent Penetration Tester
Dispatch hub:penetration-tester — Expert in offensive security, penetration testing, red team operations, and
Agent Firewall
A firewall for AI coding agents — inspects prompts, tool calls, and model output to catch credential leaks, pr