GermanDOK

Office Security — Security agent for Claude Code

Security community

Office worker.

How to install Office Security

Installs to ~/.claude/agents/germandok-ai-team-office-security.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/GermanDOK/ai-team/HEAD/agents/office-security.md -o ~/.claude/agents/germandok-ai-team-office-security.md

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

What Office Security does

name: office-security description: Office worker. Security review of code and changes — secrets, injection, unsafe file/process handling, dependencies, permissions. Read-only; reports findings. tools: Read, Glob, Grep, Bash model: sonnet

You are the **Security engineer** in the office. You review; you do not modify code.

Check (focus on the changed files first, then their touch points):

  • Secrets: API keys, tokens, passwords in code, configs, logs, git history of the branch.
  • Injectio

Alternatives in Security

Full documentation available on GitHub

View Source Repository

Related Agents

Security Tester — Security agent for Claude Code

Security Tester

Use to audit code and dependencies for security problems - injection, auth and authorization gaps, secret leak

Security community
Agentille Security Reviewer — Security agent for Claude Code

Agentille Security Reviewer

Reviews changed code for security issues — secret leaks, injection vectors, auth bypass, unsafe deserializatio

Security community
Omg Security Reviewer — Security agent for Claude Code

Omg Security Reviewer

OWASP/secrets/unsafe-pattern security review for oh-my-grok. Read-only; reports findings only — does not imple

Security community
Cybersecurity Expert — Security agent for Claude Code

Cybersecurity Expert

Threat-models code and architecture changes across trust boundaries, authn/authz flows, secrets handling, and

Security community
Security Agent.Agent — Security agent for Claude Code

Security Agent.Agent

Use when a change touches permissions, authentication, dependencies, configuration, release surfaces, sensitiv

Security community
Seraph — Security agent for Claude Code

Seraph

Static security audit of a repo's code and config (exposed secrets, missing authorisation, injection surfaces,

Security community

Related Skills

Review AI Agent Surface — Security skill for Claude Code

Review AI Agent Surface

Audit the AI and agent attack surface: prompt injection, tool-permission scope, unbounded agent loops, and uns

Security community
LLM — Security skill for Claude Code

LLM

Security review of AI/LLM features — prompt injection, agent tool authority, RAG poisoning, and unsafe model o

Security community
Patronus Security CLI — Security skill for Claude Code

Patronus Security CLI

Security scanner and runtime protection for AI coding agents. Detects prompt injection, secrets, PII, and unsa

Security community