Threat Model

What PraisonAI trusts, what it does not, and which guard rails are not security boundaries

PraisonAI trusts you, the operator, and treats everything the model reads or writes as untrusted. This page shows where that line sits, so you know which settings protect you and which only prevent accidents.

Diagram

Untrusted

Trusted: the operator

👤 Operator config, env, installed code

🤖 Agent

💬 Model output

🌐 Fetched content

📁 Cloned project files

🔌 Network peers

🛠️ Tools

🖧 Server

📦 Isolating sandbox

Trust boundaries

A vulnerability is untrusted input crossing to the trusted side without your consent: running code, reading or writing files you did not allow, reaching secrets, or acting through a server without authorisation.

Not a security boundary

FeatureWhy it is not a boundary
Python code execution: ExecutionConfig(code_mode=...) set to "safe", "unsafe" or "isolated"Runs on your machine as your OS user, in the agent process or a local subprocess. Restricted builtins, import filters and resource limits are guard rails.
TypeScript codeMode toolRuns in a Node.js vm context, which is not a sandbox.
String-based shell command filtersAllow or deny patterns over a command line can be worded around.

A way around these is a hardening bug. Report it as a normal public issue, not a security advisory.

Run untrusted code in an isolating sandbox

When the model writes code, or the code comes from someone else, run it in a backend from praisonai-sandbox that isolates it from your machine.

bash
pip install "praisonai-sandbox[docker]"
BackendWhere code runs
dockerA local container
sandlockA Landlock and seccomp sandbox (Linux)
e2b, modal, daytona, novitaA remote cloud sandbox
sshA remote machine you control
subprocessYour machine, as your user: not isolation

Network servers

Agents can be served over HTTP, MCP, A2A and AG-UI. Bind addresses differ between entry points, and some default to all interfaces, so set the host yourself.

  1. Bind to loopback

    Use host="127.0.0.1" unless other machines must reach the server.

  2. Put a token in front of anything exposed

    Use the server’s token option, or an authenticating reverse proxy.

python
from praisonaiagents import Agent

agent = Agent(instructions="Answer questions")
agent.launch(port=8000)  # HTTP, binds to 127.0.0.1 by default

Agent.launch() over HTTP binds to 127.0.0.1 by default. On any other address it requires a bearer token: set PRAISONAI_LAUNCH_AUTH_TOKEN, or one is generated and printed at start-up.

Reporting a vulnerability

What a report needs
  • A working proof of concept against the latest release, in its default configuration.
  • One report per root cause.
  • A way around an earlier fix goes on the original advisory, not a new report.
  • Scanner or AI-tool output without a tested proof of concept is closed.
Response targets
StepTarget
Acknowledge3 working days
Decision14 days
Fix for a confirmed high or critical issue30 days

Maintainers assign severity with CVSS 3.1, scored against the default configuration.

Other repositories

praisonai-platform and PraisonAI UI (aiui) take reports in their own repositories: praisonai-platform and PraisonAIUI.

Related