The Vulnerability Apple fixed a major security vulnerability in their image handling framework for both desktop and mobile devices on August 18, 2026. The vulnerability, which is tracked as CVE-2026-65346,...
Critical Flaw Disclosed in Building Automation System A serious vulnerability in Johnson Controls’ Metasys building automation technology was reported in an industrial security alert (ICSA-26-225-14) released by CISA on August...
Intel's Arc G3 Extreme delivers class-leading handheld gaming performance, strong efficiency, and a major leap over the company's previous-generation mobile graphics.
A new Warner Bros. Discovery lawsuit against Amazon, accusing the tech giant of poaching a top HBO Max marketing executive 16 months before her contract expired, comes with an unusual request: a court order barring Amazon from hiring any employee of the media conglomerate as long as they’re under contract.
The suit, filed July 21 in Los Angeles County Superior Court, centers on Pia Barlow, the longtime HBO Max executive who was announced last week as Amazon MGM Studios’ new head of series marketing. Her Warner Bros. Discovery contract ran through October 2027.
She resigned in June and was due to start at Amazon on Aug. 3.
Warner Bros. Discovery accuses Amazon of “hurriedly seeking to pirate away a number of contracted employees,” calling the company a “digital bull in a china shop” that chose to build its entertainment workforce by raiding Hollywood rather than hiring from scratch.
The suit says Amazon tried weeks earlier to recruit another WBD executive under contract through December 2027 and failed, and was pursuing at least one more when the suit was filed.
The complaint says Barlow’s departure “conveyed a troublesome message throughout Plaintiffs’ executive ranks” — that contractual commitments could be disregarded “whenever a larger paycheck appears.”
Amazon declined to comment in response to GeekWire’s inquiry.
It’s led by Mike Hopkins, head of Prime Video and Amazon MGM Studios.
Warner Bros. Discovery itself is in the middle of being sold. Paramount Skydance agreed in February to buy the company for about $81 billion, outbidding Netflix, but 12 state attorneys general sued this month to block the deal, and Paramount has pushed its closing deadline to as late as June 2027.
The complaint goes further, alleging Amazon didn’t just recruit Barlow but also picked her lawyer. Warner Bros. Discovery says the firm now representing her is based less than a mile from Amazon’s Seattle headquarters and “has a well-publicized, long-standing relationship with Amazon as outside litigation counsel,” and that Amazon is paying its fees. The firm isn’t named in the complaint.
Barlow, who lives and works in Los Angeles, is not a defendant.
Warner Bros. Discovery says its lawyers exchanged letters with Amazon and with that attorney before filing suit, demanding Barlow not leave. It makes the fee allegation on “information and belief,” a legal phrase indicating a claim based on inference rather than direct evidence.
OpenClaw, which was previously known as Clawdbot and Moltbot, is today one of the most successful and fast‑growing ecosystems for AI agents, recognized worldwide. The project quickly became popular with users because of its flexibility and ability to solve fairly complex tasks that previously required a lot of time for automation and execution. A dedicated marketplace appeared quickly after the project started gaining traction, where developers and users began publishing tools that integrate with OpenClaw. Currently, employees all over the world use OpenClaw to automate their tasks, often unaware of risks this practice introduces to them and their employers.
In this article we will examine several security aspects of OpenClaw, look at how attackers can target this system, which vulnerabilities are already known, and how to protect your organization against these issues.
OpenClaw skills
The project’s success was ensured by the fact that the agent accepts natural language instructions, does not require knowledge of programming languages, and allows the use of skills, which expand its capabilities. The overall architecture of OpenClaw can be seen below:
The OpenClaw overall architecture
As shown in the diagram, the system is designed to be used with agent skills. These skills can reside locally on the system where the agent is installed or they can be obtained from external sources. At the time of writing this article, a dedicated hub named “ClawHub” is used for sharing skills with other users.
One of the key features of OpenClaw skills is that they are easy to create and do not require coding. A skill is in essence a set of commands written in natural language, although it can contain code. Currently, there is a general description of the skill format: it is usually a text file named SKILL.md, although more complex variants may exist. The primary requirement for these files is that they use a plaintext format. To illustrate what this looks like, here is a fragment of a skill:
Openclaw skill example
The applications for OpenClaw skills are quite broad and can include everyday tasks like checking email, performing routine operations and calculations on a computer, as well as more complex pipelines that handle testing, research, or software development. For most actions, the agent requires access to the operating system’s file system, as well as to the tokens and keys of the systems it will interact with. All necessary data are usually provided by users either through environment variables or in plaintext files located alongside the agent.
Since many skills enable automation of work processes, employees worldwide actively use them. This fact, combined with the widespread adoption of the system and the overall popularity of artificial‑intelligence technologies, has attracted attackers to the project.
OpenClaw vulnerabilities
In less than two years, around 530 vulnerabilities have been discovered both in OpenClaw itself and in the underlying technologies. That said, the publication of OpenClaw vulnerabilities in the CVE database began only in February 2026. Below is a breakdown of these vulnerabilities by severity.
As shown in the chart, the number of high-severity vulnerabilities is quite large. Most of these vulnerabilities fundamentally involve issues with storing sensitive data and operating with excessively high privileges. Each of them can be exploited to hijack the agent or inject commands that it will execute.
Malicious skills
Besides exploiting vulnerabilities and deceiving users, there are more specific attack vectors against OpenClaw, namely, skills.
Research logically draws a parallel between supply‑chain attacks and the distribution of malicious skills. However, unlike usual supply-chain attacks, creating malicious skills is trivial because there is no longer a need to develop custom malware. Despite this, until February 7, 2026, no skills had undergone even a basic security check, which allowed malicious skills to appear immediately. Our scan of the skill hub in April identified 24 accounts that were distributing more than 600 malicious skills. Overall, open‑source intelligence indicates that over 1100 malicious accounts have been created since January.
Following the investigations and a lengthy effort to clean the skill repository of malicious entries, it was announced that files would undergo preliminary scanning with VirusTotal (VT) and NVIDIA’s SkillSpector. On the one hand, this is a more responsible approach to publishing skills; on the other, because OpenClaw is primarily an agent that executes a set of instructions, detecting malicious activity moves to a different level. Now it is necessary not only to analyze a file for dangerous commands that should be blocked, but also to examine all possible malicious behaviors that could be triggered by a harmful instruction within a skill. An example of a malicious command in natural language:
Example of a malicious command within a skill action
An example of a malicious command using a part of a bash command:
Malicious command inside a skill
The example in the image and similar malicious skills are detected by Kaspersky products as HEUR:Trojan.ANSI.MalClaw.gen.
In addition, Kaspersky products monitor malicious OpenClaw skill activity on the system. Below are detection statistics from our systems that have identified malicious OpenClaw client behavior. The data for June cover the first half of the month.
Statistics on Kaspersky product detections of OpenClaw malware (download)
As shown in the chart, even despite the measures taken to counter the publication of malicious skills, attacks continue. Therefore, it is important to employ layered protection that isolates the OpenClaw agent from critical data and infrastructure systems. We also recommend checking all skills that enter the organization’s perimeter. For this purpose, Kaspersky Scan Engine is suitable. This solution is designed to protect web applications, proxy servers, network attached storage, and mail gateways. It can be integrated into almost any application, and it is easy to deploy and manage.
Malicious skill detected by Scan Engine
Additionally, monitor network accesses used by the agent. For this purpose, the project already provides a sandboxing subsystem and various wrappers for working with APIs and services. Last but not least, develop a comprehensive AI policy and make sure your employees never use third-party tools that they are not explicitly allowed to use.
Login
Digital Trends
GeekWire
