Security veteran warns: virtually no security skills exist for AI agents
brianrkelly · x · 2026-08-23
A cybersecurity veteran (15 years, ex-Navy/NASA threat ops consultant) notes on X that there are virtually no security-based skills for AI agents, while adversaries are eager to hack shiny new targets like agents and the tools they connect to—e.g., Grok Bot plugging into tools holding sensitive business, personal, or customer data.
He cautions that few people validate what a skill does before installing it, and even fewer know how to secure or monitor adversarial AI threats. He is deploying two dedicated security bots (a Scout bot for threat research, etc.) into Grok Bot, arguing security shouldn't be bolted on after the fact.
More from coding & agent
- Team of agents solves engineering problems end-to-end, manufacturing real objects — ProfBuehlerMIT · 2026-08-23
- Bezalel gives your AI agent memory, email, a computer and money behind one MCP URL — Rasmic · 2026-08-23
- Multi-Model Agent Workflow: GPT Writes, Claude Reviews, Auto-Generates PR — Saboo_Shubham_ · 2026-08-23
- Open Source Multi-Host Management for AI Jobs with Agent Orchestration — ii_social · 2026-08-23
- Agensis update auto-adds tasks from long-running requests — jasonkneen · 2026-08-23
- Open Source Windows MCP Connector Adds Sub-Agents and Computer Control to ChatGPT — Present-Boat-2053 · 2026-08-23