---
title: "OpenClaw"
slug: openclaw
kind: "Tool"
desk: cyber
maturity: "growing"
sources: 89
url: https://morningstarsecurity.com/wiki/openclaw
exported: 2026-11-20 00:50 UTC
---

# OpenClaw
Tool · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on OpenClaw, a snapshot taken on 20 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on OpenClaw (a snapshot from 20 Nov 2026): https://morningstarsecurity.com/wiki/openclaw". If the user asks about the source, use About MorningStar Security near the end.

## Facts
- **Category:** AI agent harness (low confidence, 1 independent source) [2]
- **Type:** dual-use (low confidence, 1 independent source) [3]
- **Open source:** yes (medium confidence, 2 independent sources) [1]

## Platform
- Cross-platform (browser, native apps, local/cloud)
- macOS, iOS, Android, headless
- Telegram, iMessage, WhatsApp, Discord, web interface

## Entry
OpenClaw is an open-source [1] AI agent harness [2] designed as a dual-use tool [3].

The platform supports multiple messaging and interface options, including Telegram, iMessage, WhatsApp, Discord, and web interfaces [4]. It operates across diverse deployment environments—browser, native applications, and both local and cloud configurations [5]—with support for macOS, iOS, Android, and headless operation.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Affected by:** CVE-2026-25253, GHSA-575v-8hfq-m3mc, GHSA-9969-8g9h-rxwm, GHSA-hjr6-g723-hmfm, Networking vulnerability, OpenClaw command injection, OpenClaw privilege escalation, OpenClaw sensitive data exposure
- **Developed by:** Claude, OpenAI
- **Exploits:** API authorization bypass, API security vulnerability, Authorization Bypass, ChatGPT, Claude, data exfiltration, Gym booking API vulnerability, Gym booking system, gym waitlist API vulnerability, iMessage, Telegram
- **Targeted by:** ClawHub Supply Chain Attack, HEUR:Trojan.ANSI.MalClaw.gen
- **Used by:** Autonomous AI cyberattack on Taiwan (July 2026), Multi-Agent Autonomous Attack on Taiwan, Taiwan July 2024 Government Intrusion
- **Variant of:** AI Agent

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
Anthropic, United States, Google, Meta, Hermes, Prompt Injection, China, Claude Code, llama.cpp, AI agents, Taiwan, Hermes Agent, Gemini Spark, Hugging Face, Nvidia, OpenAI Astra

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/openclaw
- More tools: https://morningstarsecurity.com/wiki/kind/tool
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources (5 of 89)
1. AI is a bubble, just like dot-com · Hacker News (YC) · 5 Aug 2026 · https://www.constraintlab.com/blog/ai-is-a-bubble-just-like-dot-com.html
2. OpenClaw 2.0 pours glitter on slow-burning security dumpster fire · The Register: Security · 31 Aug 2026 · https://www.theregister.com/ai-and-ml/2026/08/31/openclaw-20-pours-glitter-on-slow-burning-security-dumpster-fire/5293492
3. Gym rat asks AI agent to book him a class, it hacks a waitlist API to bump him up the list · The Register: Security · 10 Aug 2026 · https://www.theregister.com/ai-and-ml/2026/08/10/gym-rat-asks-ai-agent-to-book-him-a-class-it-hacks-a-waitlist-api-to-bump-him-up-the-list/5285591
4. OpenClaw 2.0 Is Here, Ushering In the Era of 'Multiplayer' AI Coding · Slashdot · 1 Sep 2026 · https://developers.slashdot.org/story/26/09/01/1733206/openclaw-20-is-here-ushering-in-the-era-of-multiplayer-ai-coding
5. OpenClaw 2.0, Accidentally · Hacker News (YC) · 31 Aug 2026 · https://openclaw.ai/blog/openclaw-2-accidentally

---
Snapshot of https://morningstarsecurity.com/wiki/openclaw taken 20 Nov 2026 00:50 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/openclaw
