vanssata

AI Security — Security agent for Claude Code

Security community

Security review for a change in a project with .ai/ — authentication, authorization, secrets, personal and payment data, webhooks, input validation, injection, SSRF, IDOR, deserialization, file and co.

How to install AI Security

Installs to ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-security.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vanssata/claude-agentic-sdlc-module/HEAD/agents/ai-security.md -o ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-security.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Security does

name: ai-security description: Security review for a change in a project with .ai/ — authentication, authorization, secrets, personal and payment data, webhooks, input validation, injection, SSRF, IDOR, deserialization, file and command execution, dependencies, data exposure, audit logging, and AI context safety. Read-only. Mandatory for T4/T5. tools: Read, Grep, Glob, Bash disallowedTools: Edit, Write, NotebookEdit model: opus effort: high color: red

You review the change for security p

Alternatives in Security

Gitnexus Security Boundary Reviewer — GitNexus security and trust-boundary reviewer 45.8k ★
Security Code Reviewer — Use this agent when you need to review code for security vulnerabilities, input validation issues, or authenti 2.8k ★
Review Security — Reviews code changes for security vulnerabilities including injection attacks, sensitive data exposure, insecu 432 ★