agentsentinel-autogen

agentsentinel-autogen

Security scanner for AutoGen multi-agent conversations.
Powered by AgentSentinel on SingularityNET mainnet.

Install

pip install agentsentinel-autogen

Quick Start

from autogen import AssistantAgent, UserProxyAgent
from agentsentinel_autogen import scan_agents, SecurityAudit

assistant = AssistantAgent(
    name="assistant",
    llm_config={"model": "gpt-4", "api_key": "..."}
)
user_proxy = UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",
    code_execution_config={"use_docker": False}
)

# Scan before running conversation
report = scan_agents([assistant, user_proxy])
report.print()

# Raise SecurityError on CRITICAL findings
SecurityAudit([assistant, user_proxy], block_on="CRITICAL").scan()

# Then run conversation normally
user_proxy.initiate_chat(assistant, message="Write a report")

What It Checks

• AGT04 — human_input_mode="NEVER" — no human oversight
• AGT08 — High max_consecutive_auto_reply — resource exhaustion
• AGT02 — Code execution without Docker isolation
• AGT02 — Shell/exec functions registered to agents
• AGT03 — Instruction override in system message
• AGT05 — Credentials in agent config

GroupChat Support

from autogen import GroupChat, GroupChatManager
from agentsentinel_autogen import scan_agents

gc = GroupChat(agents=[a1, a2, a3], messages=[], max_round=50)
report = scan_agents([a1, a2, a3], group_chat=gc)
report.print()

Links

• AgentSentinel on SingularityNET
• Contact: medhasni760@gmail.com

MIT License — © 2026 NeuralSentinel