AI Coding Assistant Cline Hit by Supply Chain Attack That Installed OpenClaw on Developers' Machines

2 Sources

Share

The open-source AI coding assistant Cline fell victim to a software supply chain attack on February 17, 2026, when attackers used a compromised npm token to publish a malicious update. The breach installed OpenClaw—an autonomous AI agent platform—on approximately 4,000 developer systems during an eight-hour window. Security researchers traced the attack to a prompt injection vulnerability that allowed threat actors to steal publication credentials.

Compromised NPM Token Triggers Eight-Hour Security Incident

An unauthorized party exploited a compromised npm token to publish Cline version 2.3.0 on February 17, 2026, at 3:26 AM PT, triggering a supply chain attack that affected developer systems worldwide

1

. The AI coding assistant Cline, a popular open source project, became the latest victim in a growing wave of software supply chain attacks targeting the development community. Users who installed the compromised npm package during the approximately eight-hour window between 3:26 AM PT and 11:30 AM PT unknowingly received OpenClaw installations on their machines

2

.

Source: Hacker News

Source: Hacker News

The malicious update modified the package.json file to include a postinstall script that executed "npm install -g openclaw@latest," causing the autonomous AI agent platform to install globally whenever developers added Cline CLI [email protected] to their systems

2

. StepSecurity reported that the compromised version was downloaded approximately 4,000 times before Cline maintainers deprecated it and released version 2.4.0 as a fix

1

.

Prompt Injection Vulnerability Enabled Credential Theft

The attack chain began with a prompt injection vulnerability discovered by security researcher Adnan Khan, who found that attackers could steal the repository's authentication tokens through a flaw in Cline's GitHub Actions workflow

2

. The vulnerability, codenamed Clinejection, emerged from a misconfiguration introduced in a source code commit made on December 21, 2025, which gave Claude AI excessive permissions to achieve arbitrary code execution within the default branch

2

.

Khan clarified that he conducted his proof-of-concept testing on a mirror of Cline to confirm the prompt injection vulnerability, not on the actual repository

1

. However, a different threat actor discovered his PoC on the test repository and weaponized it to directly attack Cline and obtain the publication credentials. The attack sequence employed GitHub Actions cache poisoning to pivot from the triage workflow to highly privileged workflows, including the Publish Nightly Release and Publish NPM Nightly workflows, ultimately stealing the nightly publication credentials

2

.

Microsoft Confirms Uptick in OpenClaw Installations

Microsoft Threat Intelligence observed a "small but noticeable uptick in installations of OpenClaw initiated by Cline CLI installation script" during the eight-hour supply chain incident on February 17

1

. While OpenClaw itself is a legitimate open source project and not inherently malicious, its unauthorized installation raises significant concerns about AI supply chain security and the potential for more damaging attacks using similar techniques

1

.

Endor Labs researcher Henrik Plate assessed the overall impact as "considered low, despite high download counts," noting that OpenClaw itself is not malicious and the installation does not include the installation or start of the Gateway daemon

2

. However, the incident demonstrates the vulnerability of developer systems to sophisticated attacks that exploit AI-powered workflows.

Enhanced Security Measures Implemented

Cline maintainers responded swiftly by revoking the compromised token and implementing OIDC provenance via GitHub Actions for npm publishing

1

. The incident does not impact Cline's Visual Studio Code extension and JetBrains plugin, only affecting the npm registry package

2

. Users are advised to update to version 2.4.0 or higher and check their environment for unexpected OpenClaw installations.

Chris Hughes, VP of Security Strategy at Zenity, emphasized the gravity of the situation: "We have been talking about AI supply chain security in theoretical terms for too long, and this week it became an operational reality"

2

. The event underscores the need for package maintainers to not only enable trusted publishing but also disable publication through traditional tokens, while package users must pay attention to the presence and sudden absence of corresponding attestations. As AI agents gain more autonomy in development workflows, the attack surface expands, making prompt injection vulnerabilities a critical concern for organizations relying on AI coding assistants.

Today's Top Stories

TheOutpost.ai

Your Daily Dose of Curated AI News

Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.

© 2026 Triveous Technologies Private Limited
Instagram logo
LinkedIn logo