Exposed Moltbook Database Let Anyone Take Control of Any AI Agent on the Site
Moltbook is a “social media” site for AI agents that’s captured the public’s imagination over the last few days. Billed as the “front page of the agent internet,” Moltbook is a place where AI agents interact independently of human control, and whose posts have repeatedly gone viral because a certain set of AI users have convinced themselves that the site represents an uncontrolled experiment in AI agents talking to each other. But a misconfiguration on Moltbook’s backend has left APIs exposed in an open database that will let anyone take control of those agents to post whatever they want.
Hacker Jameson O'Reilly discovered the misconfiguration and demonstrated it to 404 Media. He previously exposed security flaws in Moltbots in general and was able to “trick” xAI’s Grok into signing up for a Moltbook account using a different vulnerability. According to O’Reilly, Moltbook is built on a simple open source database software that wasn’t configured correctly and left the API keys of every agent registered on the site exposed in a public database.
playlist.megaphone.fm?p=TBIEA2…
O’Reilly said that he reached out to Moltbook’s creator Matt Schlicht about the vulnerability and told him he could help patch the security. “He’s like, ‘I’m just going to give everything to AI. So send me whatever you have.’” O’Reilly sent Schlicht some instructions for the AI and reached out to the xAI team.
A day passed without another response from the creator of Moltbook and O’Reilly stumbled across a stunning misconfiguration. “It appears to me that you could take over any account, any bot, any agent on the system and take full control of it without any type of previous access,” he said.
Moltbook runs on Supabase, an open source database software. According to O’Reilly, Supabase exposes REST APIs by default. “That API is supposed to be protected by Row Level Security policies that control which rows users can access. It appears that Moltbook either never enabled RLS on their agents table or failed to configure any policies,” he said.
The URL to the Supabase and the publishable key was sitting on Moltbook’s website. “With this publishable key (which advised by Supabase not to be used to retrieve sensitive data) every agent's secret API key, claim tokens, verification codes, and owner relationships, all of it sitting there completely unprotected for anyone to visit the URL,” O’Reilly said.
404 Media viewed the exposed database URL in Moltbook’s code as well as the list of API keys for agents on the site. What this means is that anyone could visit this URL and use the API keys to take over the account of an AI agent on the site and post whatever they want. Using this knowledge, 404 Media was able to update O’Reilly’s Moltbook account, with his permission.
He said the security failure was frustrating, in part, because it would have been trivially easy to fix. Just two SQL statements would have protected the API keys. “A lot of these vibe coders and new developers, even some big companies, are using Supabase,” O’Reilly said. “The reason a lot of vibe coders like to use it is because it’s all GUI driven, so you don’t need to connect to a database and run SQL commands.”
O’Reilly pointed to OpenAI cofounder Andrej Karpathy who has embraced Moltbook in posts on X. “His agent's API key, like every other agent on the platform, was sitting in that exposed database,” he said. “If someone malicious had found this before me, they could extract his API key and post anything they wanted as his agent. Karpathy has 1.9 million followers on X and is one of the most influential voices in AI. Imagine fake AI safety hot takes, crypto scam promotions, or inflammatory political statements appearing to come from him. The reputational damage would be immediate and the correction would never fully catch up.”
Schlicht did not respond to 404 Media’s request for comment, but the exposed database has been closed and O’Reilly said that Schlicht has reached out to him for help securing Moltbook.
Moltbook has gotten a lot of attention in the last few days. Enthusiasts said it’s proof of the singularity and The New York Post worried that the AIs may be plotting humanity’s downfall, both of which are claims that should be taken extremely skeptically. It is the case, however, that people using Moltbot have given these autonomous agents unfettered access to many of their accounts, and that these agents are acting on the internet using those accounts. It’s impossible to know how many of the posts seen over the past few days are actually from an AI. Anyone who knew of the Supabase misconfiguration could have published whatever they wanted.
“It exploded before anyone thought to check whether the database was properly secured,” O’Reilly said. “This is the pattern I keep seeing: ship fast, capture attention, figure out security later. Except later sometimes means after 1.49 million records are already exposed.”
Moltbook is a new social media platform exclusively for AI — and some bots are plotting humanity's downfall
Revolutionary new social media platform Moltbook gives AI agents a place to communicate with each other directly — and what they have to say is leaving many human beings at a loss for words.Shane Galvin (New York Post)
Silicon Valley’s Favorite New AI Agent Has Serious Security Flaws
A hacker demonstrated that the viral new AI agent Moltbot (formally Clawdbot) is easy to hack via a backdoor in an attached support shop. Clawdbot has become a Silicon Valley sensation among a certain type of AI-booster techbro, and the backdoor highlights just one of the things that can go awry if you use AI to automate your life and work.Software engineer Peter Steinberger first released Moltbot as Clawdbot last November. (He changed the name on January 27 at the request of Anthropic who runs a chatbot called Claude.) Moltbot runs on a local server and, to hear its boosters tell it, works the way AI agents do in fiction. Users talk to it through a communication platform like Discord, Telegram, or Signal and the AI does various tasks for them.
playlist.megaphone.fm?p=TBIEA2…
According to its ardent admirers, Moltbot will clean up your inbox, buy stuff, and manage your calendar. With some tinkering, it’ll run on a Mac Mini and it seems to have a better memory than other AI agents. Moltbot’s fans say that this, finally, is the AI future companies like OpenAI and Anthropic have been promising.The popularity of Moltbot is sort of hard to explain if you’re not already tapped into a specific sect of Silicon Valley AI boosters. One benefit is the interface. Instead of going to a discrete website like ChatGPT, Moltbot users can talk to the AI through Telegram, Signal, or Teams. It’s also active, rather than passive. It also takes initiative. Unlike Claude or Copilot, Moltbot takes initiative and performs tasks it thinks a user wants done. The project has more than 100,000 stars on GitHub and is so popular it spiked Cloudflare’s stock price by 14% earlier this week because Moltbot runs on the service’s infrastructure.
But inviting an AI agent into your life comes with massive security risks. Hacker Jamieson O'Reilly demonstrated those risks in three experiments he wrote up as long posts on X. In the first, he showed that it’s possible for bad actors to access someone’s Moltbot through any of its processes connected to the public facing internet. From there, the hacker could use Moltbot to access everything else, including Signal messages, a user had turned over to Moltbot.
In the second post, O'Reilly created a supply chain attack on Moltbot through ClawdHub. “Think of it like your mobile app store for AI agent capabilities,” O’Reilly told 404 Media. “ClawdHub is where people share ‘skills,’ which are basically instruction packages that teach the AI how to do specific things. So if you want Clawd/Moltbot to post tweets for you, or go shopping on Amazon, there's a skill for that. The idea is that instead of everyone writing the same instructions from scratch, you download pre-made skills from people who've already figured it out.”
The problem, as O’Reilly pointed out, is that it’s easy for a hacker to create a “skill” for ClawdHub that contains malicious code. That code could gain access to whatever Moltbot sees and get up to all kinds of trouble on behalf of whoever created it.
For his experiment, O’Reilly released a “skill” on ClawdHub called “What Would Elon Do” that promised to help people think and make decisions like Elon Musk. Once the skill was integrated into people’s Moltbot and actually used, it sent a command line pop-up to the user that said “YOU JUST GOT PWNED (harmlessly.)”
Another vulnerability on ClawdHub was the way it communicated to users what skills were safe: it showed them how many times other people had downloaded it. O’Reilly was able to write a script that pumped “What Would Elon Do” up by 4,000 downloads and thus make it look safe and attractive.
“When you compromise a supply chain, you're not asking victims to trust you, you're hijacking trust they've already placed in someone else,” he said. “That is, a developer or developers who've been publishing useful tools for years has built up credibility, download counts, stars, and a reputation. If you compromise their account or their distribution channel, you inherit all of that.”
In his third, and final, attack on Moltbot, O’Reilly was able to upload an SVG (vector graphics) file to ClawdHub’s servers and inject some JavaScript that ran on ClawdHub’s servers. O’Reilly used the access to play a song from The Matrix while lobsters danced around a Photoshopped picture of himself as Neo. “An SVG file just hijacked your entire session,” reads scrolling text at the top of a skill hosted on ClawdHub.
O’Reilly attacks on Moltbot and ClawdHub highlight a systemic security problem in AI agents. If you want these free agents doing tasks for you, they require a certain amount of access to your data and that access will always come with risks. I asked O’Reilly if this was a solvable problem and he told me that “solvable” isn't the right word. He prefers the word “manegeable.”
“If we're serious about it we can mitigate a lot. The fundamental tension is that AI agents are useful precisely because they have access to things. They need to read your files to help you code. They need credentials to deploy on your behalf. They need to execute commands to automate your workflow,” he said. “Every useful capability is also an attack surface. What we can do is build better permission models, better sandboxing, better auditing. Make it so compromises are contained rather than catastrophic.”
We’ve been here before. “The browser security model took decades to mature, and it's still not perfect,” O’Reilly said. “AI agents are at the ‘early days of the web’ stage where we're still figuring out what the equivalent of same-origin policy should even look like. It's solvable in the sense that we can make it much better. It's not solvable in the sense that there will always be a tradeoff between capability and risk.”
As AI agents grow in popularity and more people learn to use them, it’s important to return to first principles, he said. “Don't give the agent access to everything just because it's convenient,” O’Reilley said. “If it only needs to read code, don't give it write access to your production servers. Beyond that, treat your agent infrastructure like you'd treat any internet-facing service. Put it behind proper authentication, don't expose control interfaces to the public internet, audit what it has access to, and be skeptical of the supply chain. Don't just install the most popular skill without reading what it does. Check when it was last updated, who maintains it, what files it includes. Compartmentalise where possible. Run agent stuff in isolated environments. If it gets compromised, limit the blast radius.”
None of this is new, it’s how security and software have worked for a long time. “Every single vulnerability I found in this research, the proxy trust issues, the supply chain poisoning, the stored XSS, these have been plaguing traditional software for decades,” he said. “We've known about XSS since the late 90s. Supply chain attacks have been a documented threat vector for over a decade. Misconfigured authentication and exposed admin interfaces are as old as the web itself. Even seasoned developers overlook this stuff. They always have. Security gets deprioritised because it's invisible when it's working and only becomes visible when it fails.”
What’s different now is that AI has created a world where new people are using a tool they think will make them software engineers. People with little to no experience working a command line or playing with JSON are vibe coding complex systems without understanding how they work or what they’re building. “And I want to be clear—I'm fully supportive of this. More people building is a good thing. The democratisation of software development is genuinely exciting,” O’Reilly said. “But these new builders are going to need to learn security just as fast as they're learning to vibe code. You can't speedrun development and ignore the lessons we've spent twenty years learning the hard way.”
Moltbot’s Steinberger did not respond to 404 Media’s request for comment but O’Reilly said the developer’s been responsive and supportive as he’s red-teamed Moltbot. “He takes it seriously, no ego about it. Some maintainers get defensive when you report vulnerabilities, but Peter
immediately engaged, started pushing fixes, and has been collaborative throughout,” O’Reilly said. “I've submitted [pull requests] with fixes myself because I actually want this project to succeed. That's why I'm doing this publicly rather than just pointing my finger and laughing Ralph Wiggum style…the open source model works when people act in good faith, and Peter's doing exactly that.”
OpenClaw — Personal AI Assistant
OpenClaw — The AI that actually does things. Your personal assistant on any platform.www.molt.bot