Skip to content

DEV Community

Umang Kumar

Founder of Cirvix: open-source runtime authorization for AI agents. Capability is not authority.

Joined on Oct 9, 2026 https://cirvix.com

Oct 11

Codex CLI and Gemini CLI Safety Settings: A Side-by-Side Hardening Guide

#ai #security #cli #devops

5 min read

Oct 11

git push --force Guardrails for AI Agents: Server, Client, and Policy Layers That Actually Hold

#git #ai #security #devops

5 min read

Oct 11

Human Approval for AI Agent Tool Calls: What to Hold, Who Approves, and How the Agent Waits

#ai #security #agents #devops

5 min read

Oct 11

Audit Logs for AI Coding Agents: What to Record, Where to Collect It, and What It Proves

#ai #security #devops #observability

5 min read

Oct 11

Protecting .env Secrets From AI Agents: Six Layers, and How to Test Each One

#security #ai #devops #webdev

5 min read

Oct 11

Prompt Injection in Coding Agents: Where It Gets In and What Actually Limits the Damage

#ai #security #llm #programming

5 min read

Oct 11

Cursor Agent Permissions Explained: What Runs Without Asking, and How to Tighten It

#cursor #security #ai #productivity

4 min read

Oct 11

MCP Server Security Risks: 7 Threats to Model Before You Connect One

#mcp #security #ai #llm

5 min read

Oct 11

How to Stop an AI Agent From Running rm -rf (and Why String Matching Isn't Enough)

#ai #security #bash #devops

5 min read

Oct 11

Claude Code Security Best Practices: A Practical Hardening Guide

#claudecode #security #ai #devops

5 min read

Oct 9

Hash-chained audit logs for AI agent actions, in 40 lines

#ai #security #mcp #devops

3 min read

Oct 9

Securing MCP servers: a practical checklist for 2026

#ai #security #mcp #devops

4 min read

Oct 9

Why approval prompts don't work as a security boundary for coding agents

#ai #security #mcp #devops

3 min read

Oct 9

5 permission rules every coding agent should ship with

#ai #security #opensource #devops

4 min read

Oct 9

Stop the read-then-exfiltrate chain: session taint for AI agents

#ai #security #opensource #mcp

4 min read

Oct 9

MCP Security: Where to Put the Authorization Boundary

#mcp #security #ai #agents

8 min read

Oct 9

AI Agent Authorization: Control What Agents Can Do

#ai #security #agents #llm

8 min read

Oct 9

Runtime Authorization for AI Agents: A Practical Guide

#ai #security #agents #opensource

9 min read

loading...