Exploit Authz — Research agent for Claude Code
Authorization exploitation and privilege escalation.
How to install Exploit Authz
Installs to ~/.claude/agents/us-shannon-on-claude-code-exploit-authz.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/us/shannon-on-claude-code/HEAD/.claude/agents/exploit-authz.md -o ~/.claude/agents/us-shannon-on-claude-code-exploit-authz.md Restart Claude Code, or start a new session, for it to be picked up.
What Exploit Authz does
name: exploit-authz description: Authorization exploitation and privilege escalation. Requires authz analysis deliverable. tools: Read, Grep, Glob, Write, Edit, Bash, Agent, mcp__playwright__*, mcp__shannon-tools__* model: claude-sonnet-4-6 maxTurns: 500
IMPORTANT: In your instructions below, wherever you see "TARGET_URL_PLACEHOLDER", use the actual target URL provided to you when this agent was launched. Wherever you see "REPO_PATH_PLACEHOLDER", your working directory IS the repo. Wher
Alternatives in Research
- Hooks: — You are a GSD codebase mapper 38.5k ★
- Attack Tree Construction — Systematic attack path visualization and analysis 31.9k ★
- Skill — Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis 31.7k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Exploit Auth
Authentication exploitation and account takeover. Requires auth analysis deliverable.
Exploit Ssrf
SSRF exploitation for internal service access. Requires SSRF analysis deliverable.
Scope Exploit
Red team operator — context-driven permission discovery, escalation path identification with real-world resear
Exploit Researcher
Vulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom ex
Gateway Notes
Purpose: the confirmed gateway/guardrail mechanisms for the workshop, input guard, output sidecar, MCP authz,
Cs Agent
CS Lead agent. Manages customer support, FAQ, escalation handling, and user feedback analysis.
Related Skills
Ad Attack Paths
Launch the ad-attack-planner agent to reason low-privilege-to-Domain-Admin paths from the collected inventory
Pentest
Run an AI-powered penetration test against a target URL + source code repo. Usage: /pentest [--config ] --ski
Engage.Exploit
Execute Phase 4 - Exploitation and Access Establishment