Radar / AI security / Puffin
Puffin: identity and inboxes for AI agents
Identity and inboxes for AI agents: a real email address, calendar, and chat seats per agent.
Why it matters
Agents finally get their own reachable identity, with human approval on every outbound message and guardrails against prompt injection.
What you could build with it
A company running customer-facing agents could give each agent its own email address and chat seat through Puffin, so customers reach the agent directly while every outbound message waits for a human approval click.
Does it hold up?
Too early to judge: launched Nov 15 with plugins published Nov 13 and no stars yet; the approval-gated messaging model is sensible, but real-world usage evidence is thin.
Built with Puffin
- puffin-local on PyPIarticle · Python SDK, CLI, and local MCP server for Puffin, with scoped agent keys and approval-gated sending.
- justpuffin/claude-code-plugingithub · Open-source plugin connecting a Puffin agent identity to Claude Code.
- justpuffin/codex-plugingithub · Open-source plugin connecting a Puffin agent identity to Codex.
- justpuffin/openclaw-plugingithub · Open-source plugin connecting a Puffin agent identity to OpenClaw.
Learn more
First spotted on article: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.