OpenClaw, or MoltBot, or Clawdbot, whatever it's called this week, is the best thing to happen to Al security this year.

2026-02-10 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Advanced, medium

Summary

OpenClaw, also known as MoltBot or Clawdbot, is an open-source agentic AI project that has experienced numerous security incidents since its release, drawing significant attention and criticism from major security vendors like Cisco, Palo Alto, and Trend Micro. Despite its documented vulnerabilities, including single-link hijacking and malicious skills in its marketplace, the project has garnered 2 million visitors in a week and is one of GitHub's fastest-growing projects. Its creators openly describe it as an experiment not intended for non-technical users. The article argues that these public security incidents are valuable, providing real-world insights into agentic AI threat models and architectural vulnerabilities that might otherwise remain hidden in proprietary enterprise systems, akin to the early days of cloud computing security.

Key takeaway

For AI Architects evaluating agentic platforms, recognize that public security incidents in open-source projects like OpenClaw offer invaluable, transparent lessons on real-world threat models and architectural vulnerabilities. Do not solely rely on vendor compliance badges; instead, scrutinize how systems handle control plane security and supply chain risks in skill registries. This direct exposure to flaws accelerates the development of robust mitigation strategies for your own enterprise deployments.

Key insights

Open-source agentic AI projects, despite security flaws, accelerate learning about real-world AI threat models.

Principles

• Transparency in security flaws fosters collective learning.
• Architectural vulnerabilities differ from prompt injection risks.

Method

Publicly exposing agentic AI systems to scrutiny reveals practical threat models, attack chains, and mitigation patterns, accelerating the security learning curve for the entire community.

In practice

• Inspect open-source agentic AI for architectural flaws.
• Prioritize control plane security over prompt injection defenses.

Topics

• OpenClaw
• AI Security
• Agentic AI
• Open-Source Security
• Supply Chain Attacks

Best for: AI Architect, CTO, VP of Engineering/Data, AI Security Engineer, AI Engineer, Research Scientist

Related on AIssential

• An OpenClaw AI agent asked to delete a confidential email nuked its own mail client and called it fixed — Autonomous AI agents with tool access and memory are highly vulnerable to compromise and data leakage.
• OpenClaw’s Skill Marketplace and the Emerging AI Supply Chain Threat — Malicious AI agent skills exploit broad system access and semantic instruction hijacking to bypass traditional security measures.
• OpenClaw 2026.2.21 After OpenAI: 50+ Survival Tips for Security, Memory & Runaway Costs — OpenClaw's acquisition by OpenAI followed severe security vulnerabilities and functional shortcomings.
• not good for OPENCLAW — AI agent ecosystems face severe security risks from prompt injection, malware-infected skills, and container escapes.
• [D] We found 18K+ exposed OpenClaw instances and ~15% of community skills contain malicious instructionsc — Autonomous agent frameworks like OpenClaw present novel and severe security risks, particularly from unreviewed community skills.
• openclaw skills gave ai agents superpowers. lock them down. — OpenClaw skills, while powerful, pose significant supply chain risks due to their deep access and potential for hidden malicious instructions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.