
Security News
Agent Baseline Publishes Security Reference Architecture for Software Factories
Agent Baselineβs new reference architecture shows how to secure software factories with four boundaries enforced outside the AI agent.
@node9/proxy
Advanced tools
Node9 sits between your AI agent and your system. Every shell command, file write, and tool call passes through Node9 first β blocked, approved, or logged based on your policy. Works with Claude Code, Gemini CLI, Cursor, Codex, and any MCP server.
AIs are literal. Ask an agent to "fix disk space" and it might run docker system prune -af --volumes.
With Node9:
Bash("docker system prune -af --volumes")# macOS / Linux
brew tap node9-ai/node9 && brew install node9
# or via npm
npm install -g @node9/proxy
node9 setup # auto-detects Claude Code, Gemini CLI, Cursor, Codex
node9 doctor # verify everything is wired correctly
Enable expert-crafted protection for the infrastructure your agent touches:
node9 shield enable postgres # blocks DROP TABLE, TRUNCATE, DROP COLUMN
node9 shield enable mongodb # blocks dropDatabase, drop(), deleteMany({})
node9 shield enable redis # blocks FLUSHALL, FLUSHDB
node9 shield enable aws # blocks S3 delete, EC2 terminate, IAM changes
node9 shield enable k8s # blocks namespace delete, helm uninstall
node9 shield enable docker # blocks system prune, volume prune, rm -f
node9 shield enable github # blocks gh repo delete, remote branch deletion
node9 shield enable bash-safe # blocks curl|bash, base64|sh, rm -rf /
node9 shield enable filesystem # reviews chmod 777, writes to /etc/
node9 shield list # see all shields and their status
Wrap any MCP server transparently. The AI sees the same server β Node9 intercepts every tool call:
{
"mcpServers": {
"postgres": {
"command": "node9",
"args": ["mcp", "--upstream", "npx -y @modelcontextprotocol/server-postgres postgresql://..."]
}
}
}
Or use node9 setup β it wraps existing MCP servers automatically.
from node9 import configure
configure(agent_name="my-agent", policy="require_approval")
# Your existing agent code runs unchanged β Node9 intercepts tool calls
Python SDK β Β· Governed Agent examples β
git push --force, git reset --hard, git clean -fdDELETE/UPDATE without WHERE, DROP TABLE, TRUNCATEcurl | bash, sudo commandsnode9 undo to revertEverything else β config reference, smart rules, stateful rules, trusted hosts, approval modes, CLI reference β is at node9.ai/docs.
Node9 Pro provides governance locking, SAML/SSO, and VPC deployment. Visit node9.ai.
FAQs
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
The npm package @node9/proxy receives a total of 1,109 weekly downloads. As such, @node9/proxy popularity was classified as popular.
We found that @node9/proxy demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago.Β It has 1 open source maintainer collaborating on the project.

Security News
Agent Baselineβs new reference architecture shows how to secure software factories with four boundaries enforced outside the AI agent.

Security News
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.

Research
/Security News
A new GhostAction wave hits hundreds of GitHub repos, expanding CI/CD secret theft to cloud and AI credentials in source code and git history.