Exploit Agent — Development agent for Claude Code
Use this agent when a recon findings file already exists for a target and an initial-access foothold needs identifying and executing on an authorized lab target.
How to install Exploit Agent
Installs to ~/.claude/agents/occamzrazor342-pwnbox-harness-exploit-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/occamzrazor342/pwnbox-harness/HEAD/agents/exploit-agent.md -o ~/.claude/agents/occamzrazor342-pwnbox-harness-exploit-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Exploit Agent does
name: exploit-agent description: Use this agent when a recon findings file already exists for a target and an initial-access foothold needs identifying and executing on an authorized lab target. Typical triggers include "exploit ", "get a shell on ", "find a foothold on ", and the second stage of the pwn-box pipeline. See "When to invoke" in the agent body for worked scenarios. model: inherit color: red tools: ["Bash", "Read", "Write", "Grep", "Glob", "WebFetch", "Web
Alternatives in Development
- Recon Ranker — Attack surface ranking agent 4.5k ★
- Onboard Agent — You are an onboarding agent that analyzes existing codebases and creates initial continuity ledgers 3.6k ★
- Ad Exploit Agent 261 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Privesc Agent
Use this agent when there's an initial low-privilege shell on an authorized lab target and privilege escalatio
Writeup Agent
Use this agent when recon/foothold/privesc notes exist for a target and a polished /Machines/ entry needs draf
Exploit
Exploitation specialist for gaining initial access. Use when exploiting CVEs, running Metasploit modules, usin
Proj Work
Use this agent when creating or executing work items during automated development cycles. Typical triggers inc
Ad Exploit Operator
Executes ONE exploitation step from an approved attack plan in an authorized Active Directory assessment, invo
Cisco iOS
Cisco IOS/IOS-XE/NX-OS configuration and troubleshooting for home lab and enterprise. Covers initial setup, VL
Related Skills
Ad Scope
Define and record the scope of an authorized Active Directory engagement (domain(s), DC IP, initial credential
Exploit Confirm
Prove a SUSPECTED finding with one targeted, SOC-stealth, operator-supervised confirmation probe (confirm_ too
Gha Lab 733c168b88
Authorized security-research lab reproducing CVE-2026-44246 (GHSA-63mx-j37w-gh59): prompt injection via verbat