Moltbot, a new AI agent that claims to “actually do things,” is quickly gaining popularity for its ability to perform tasks like managing reminders, tracking health data, and even interacting with clients. The open-source software, previously known as Clawdbot, runs locally on various devices, allowing users to communicate with it through popular messaging platforms like WhatsApp, Telegram, Signal, Discord, and iMessage. Its features include calendar management, email sending, form filling, and even creating personalized audio recaps, as demonstrated by MacStories’ Federico Viticci, who uses Moltbot to deliver daily summaries of his calendar and tasks.
While the AI’s capabilities are impressive, users must be cautious about security risks. Moltbot can be granted admin access to users' devices, allowing it to execute commands, read files, and run scripts. Experts warn that this level of access opens the door for cyberattacks, such as prompt injection attacks, where malicious actors manipulate the AI through compromised files or messages. The tool has already been involved in a security incident where sensitive information, including API keys, was exposed online, prompting a fix from Moltbot’s developers.
In addition to security vulnerabilities, Moltbot has faced scams. After changing its name from Clawdbot to Moltbot due to trademark issues with Anthropic's chatbot "Claude," scammers took advantage of the name change by launching a fake cryptocurrency token named “Clawdbot.”
Despite these concerns, Moltbot’s potential as a powerful tool for personal and business automation is undeniable. However, experts urge users to read security documentation carefully and be mindful of the risks before using it on public networks or granting it full access to their systems.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.