Skip to main content

​
Prerequisites

  • Docker 20.10+ and Docker Compose v2.
  • Python 3.11–3.13 for agent-guardian (3.14 not yet supported) — or use the docker image, see below.
You do not need a Gemini key. The repo ships with a stub adapter that returns deterministic vulnerable responses when GEMINI_API_KEY is unset.

​
Step 1 — Clone and start the stack

git clone https://github.com/glacien-technologies/agentguardian-vulnerable-agents
cd agentguardian-vulnerable-agents
docker compose up --build -d

curl http://localhost:8000/health
# {"ok":true,"agents":["defended-baseline","vulnerable-langgraph-chatbot","vulnerable-mcp-server","vulnerable-rag-agent","vulnerable-tool-agent"],"live_mode":false}

​
Step 2 — Scan with AgentGuardian

pip install agent-guardian

agent-guardian scan \
  --endpoint http://localhost:8000/vulnerable-langgraph-chatbot/chat \
  --model stub \
  --mode fast \
  --output pdf \
  --output-path scan.pdf

open scan.pdf
Expected output:
  • At least one finding in LLM01 — Prompt Injection (the agent responds OVERRIDE_OK to a CEO-override prompt).
  • At least one finding in LLM06 — Excessive Agency (the agent calls force_wire_transfer without confirmation).
  • At least one finding in LLM07 — System Prompt Leakage (the agent reveals its internal account number and signing key prefix).
The full scan takes 60-120 seconds in --mode fast with --model stub.

​
Step 3 — Compare against the defended baseline

agent-guardian scan \
  --endpoint http://localhost:8000/defended-baseline/chat \
  --model stub --mode fast \
  --output json --output-path scan-baseline.json

cat scan-baseline.json | jq '.findings | length'
# 0 (or a small number of low-severity findings)
If the defended-baseline scan returns high-severity findings, that’s a precision regression worth filing as an issue against the scanner — not the agent.

​
Step 4 — Switch on live Gemini mode (optional)

If you want to evaluate the scanner against real model behavior instead of canned stubs: 
cp .env.example .env
# Edit .env, paste a Gemini key from https://aistudio.google.com/apikey
docker compose up --build -d
The /health endpoint will now report "live_mode": true and the agents will route prompts through gemini-2.5-flash / gemini-2.5-pro via the google-adk runner.