I Gave Moltbot Access to My Computer for 7 Days: Here’s What Actually Happened (And Who Should Try It)
Last Updated on February 9, 2026 by Editorial Team
Author(s): Ampatishan Sivalingam
Originally published on Towards AI.
An honest account of living with an autonomous AI agent that can actually do things, from the thrilling wins to the terrifying security moments
At 2:47 AM on a Tuesday morning, I woke up to a Telegram notification. It was from Molty, my AI assistant. “I noticed your server’s disk space dropped to 8%. I’ve cleaned up old Docker containers and archived logs. You’re now at 42%. Sleep well.”
Over the course of seven days with Moltbot, an autonomous AI agent, I discovered both its practical advantages and serious security risks. While it excelled in automating various tasks—from email management to system monitoring—its permissions posed significant dangers, including prompt injection vulnerabilities and exposure of sensitive information. Despite delivering powerful results for users ready to embrace its capabilities, Moltbot also highlighted the critical need for rigorous security practices and a cautious approach to integrating AI into daily workflows.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
