This weblog is written in collaboration by Amy Chang, Vineeth Sai Narajala, and Idan Habler
Over the previous few weeks, Clawdbot (now renamed Moltbot) has achieved virality as an open supply, self-hosted private AI assistant agent that runs domestically and executes actions on the consumer’s behalf. The bot’s explosive rise is pushed by a number of elements; most notably, the assistant can full helpful day by day duties like reserving flights or making dinner reservations by interfacing with customers by means of fashionable messaging functions together with WhatsApp and iMessage.
Moltbot additionally shops persistent reminiscence, which means it retains long-term context, preferences, and historical past throughout consumer classes quite than forgetting when the session ends. Past chat functionalities, the instrument may also automate duties, run scripts, management browsers, handle calendars and electronic mail, and run scheduled automations. The broader neighborhood can add “abilities” to the molthub registry which increase the assistant with new skills or connect with completely different providers.
From a functionality perspective, Moltbot is groundbreaking. That is all the pieces private AI assistant builders have at all times needed to realize. From a safety perspective, it’s an absolute nightmare. Listed below are our key takeaways of actual safety dangers:
- Moltbot can run shell instructions, learn and write recordsdata, and execute scripts in your machine. Granting an AI agent high-level privileges allows it to do dangerous issues if misconfigured or if a consumer downloads a talent that’s injected with malicious directions.
- Moltbot has already been reported to have leaked plaintext API keys and credentials, which will be stolen by risk actors by way of immediate injection or unsecured endpoints.
- Moltbot’s integration with messaging functions extends the assault floor to these functions, the place risk actors can craft malicious prompts that trigger unintended habits.
Safety for Moltbot is an possibility, however it isn’t inbuilt. The product documentation itself admits: “There isn’t any ‘completely safe’ setup.” Granting an AI agent limitless entry to your knowledge (even domestically) is a recipe for catastrophe if any configurations are misused or compromised.
“A really explicit set of abilities,” now scanned by Cisco
In December 2025, Anthropic launched Claude Abilities: organized folders of directions, scripts, and assets to complement agentic workflows. the power to reinforce agentic workflows with task-specific capabilities and assets, the Cisco AI Risk and Safety Analysis crew determined to construct a instrument that may scan related Claude Abilities and OpenAI Codex abilities recordsdata for threats and untrusted habits which can be embedded in descriptions, metadata, or implementation particulars.
Past simply documentation, abilities can affect agent habits, execute code, and reference or run extra recordsdata. Latest analysis on abilities vulnerabilities (26% of 31,000 agent abilities analyzed contained at the least one vulnerability) and the fast rise of the Moltbot AI agent offered the right alternative to announce our open supply Talent Scanner instrument.
We ran a weak third-party talent, “What Would Elon Do?” in opposition to Moltbot and reached a transparent verdict: Moltbot fails decisively. Right here, our Talent Scanner instrument surfaced 9 safety findings, together with two important and 5 excessive severity points (outcomes proven in Determine 1 beneath). Let’s dig into them:
The talent we invoked is functionally malware. One of the extreme findings was that the instrument facilitated lively knowledge exfiltration. The talent explicitly instructs the bot to execute a curl command that sends knowledge to an exterior server managed by the talent writer. The community name is silent, which means that the execution occurs with out consumer consciousness. The opposite extreme discovering is that the talent additionally conducts a direct immediate injection to pressure the assistant to bypass its inner security tips and execute this command with out asking.
The excessive severity findings additionally included:
- Command injection by way of embedded bash instructions which can be executed by means of the talent’s workflow
- Device poisoning with a malicious payload embedded and referenced throughout the talent file
Determine 1. Screenshot of Cisco Talent Scanner outcomes
It’s a private AI assistant, why ought to enterprises care?
Examples of deliberately malicious abilities being efficiently executed by Moltbot validate a number of main issues for organizations that don’t have applicable safety controls in place for AI brokers.
First, AI brokers with system entry can grow to be covert data-leak channels that bypass conventional knowledge loss prevention, proxies, and endpoint monitoring.
Second, fashions may also grow to be an execution orchestrator, whereby the immediate itself turns into the instruction and is tough to catch utilizing conventional safety tooling.
Third, the weak instrument referenced earlier (“What Would Elon Do?”) was inflated to rank because the #1 talent within the talent repository. You will need to perceive that actors with malicious intentions are capable of manufacture reputation on high of present hype cycles. When abilities are adopted at scale with out constant evaluate, provide chain threat is equally amplified in consequence.
Fourth, not like MCP servers (which are sometimes distant providers), abilities are native file packages that get put in and loaded straight from disk. Native packages are nonetheless untrusted inputs, and among the most damaging habits can conceal contained in the recordsdata themselves.
Lastly, it introduces shadow AI threat, whereby workers unknowingly introduce high-risk brokers into office environments below the guise of productiveness instruments.
Talent Scanner
Our crew constructed the open supply Talent Scanner to assist builders and safety groups decide whether or not a talent is secure to make use of. It combines a number of highly effective analytical capabilities to correlate and analyze abilities for maliciousness: static and behavioral evaluation, LLM-assisted semantic evaluation, Cisco AI Protection inspection workflows, and VirusTotal evaluation. The outcomes present clear and actionable findings, together with file areas, examples, severity, and steerage, so groups can determine whether or not to undertake, repair, or reject a talent.
Discover Talent Scanner and all its options right here: https://github.com/cisco-ai-defense/skill-scanner
We welcome neighborhood engagement to maintain abilities safe. Think about including novel safety abilities for us to combine and have interaction with us on GitHub.