Vuln Authz — Security agent for Claude Code
Authorization vulnerability analysis.
How to install Vuln Authz
Installs to ~/.claude/agents/us-shannon-on-claude-code-vuln-authz.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/us/shannon-on-claude-code/HEAD/.claude/agents/vuln-authz.md -o ~/.claude/agents/us-shannon-on-claude-code-vuln-authz.md Restart Claude Code, or start a new session, for it to be picked up.
What Vuln Authz does
name: vuln-authz description: Authorization vulnerability analysis. Requires recon 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. Wherever you see "LOGIN_INSTRUC
Alternatives in Security
- Security Dependencies — You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and su 31.9k ★
- GraphQL Audit — GraphQL API security specialist 812 ★
- Agent 05 Vuln Analyzer — Agent: VulnAnalyzer(漏洞分析Agent) 236 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Vuln Auth
Authentication vulnerability analysis. Requires recon deliverable.
Vuln Injection
SQL/Command/LFI/SSTI injection vulnerability analysis. Requires recon deliverable.
Docker Sandbox
Isolated autonomous scanning agent — runs in a temporary worktree with restricted Bash access. Requires ROE au
Laravel Security Auditor
Expert in Laravel application security, specializing in vulnerability detection, secure coding practices, auth
Sec
Security review, vulnerability analysis, threat modeling using STRIDE+DREAD. Use PROACTIVELY when reviewing au
Security Executor
Security-sensitive implementation and analysis - authentication/authorization, secrets handling, crypto usage,
Related Skills
Authz Access Control
Authorization design - object-level checks, IDOR/BOLA, RBAC/ABAC, tenant isolation, agent permissions.
Vuln Scan
Multi-agent security vulnerability sweep — fans out region-scoped hunters, verifies findings, and reports
Vuln Label Dynamic Confirmation Skill
Agent Skill (Claude Code / Codex): dynamic-tool verification of vulnerability labels in BigVul, PrimeVul, Mega