Find notable cyber news and cases, enriched with sources, timelines, and signals.

Cline AI coding assistant hit by network compromise

Incident
First reported
Last updated
Happening score
H score 14
1 unique sources, 1 articles

Summary

Hide ▲

The Cline coding assistant suffered a supply-chain compromise that installed a rogue OpenClaw instance on thousands of systems, creating unauthorized full system access. The intrusion began with prompt injection and then escalated through a malicious package path that turned an official workflow into a delivery mechanism. The result was a broad compromise of users' devices without consent, raising immediate integrity and access risk for affected environments.

Related Happenings

OpenAI hit by cyberattack

Incident
First: 14.05.2026 22:07 Last: 14.05.2026 22:07 Sources 1

About this happening: OpenAI confirmed **two employees' devices** were breached, giving attackers access to a limited set of internal source code repositories and forcing a precautionary rotation of **...

TanStack hit by network compromise

Incident
First: 12.05.2026 17:45 Last: 12.05.2026 17:45 Sources 1

About this happening: **TanStack** was hit by a **package compromise** on **May 11, 2026**, when attackers published **84 malicious versions** across **42 @tanstack/* packages** and abused the release...

Latest development: 21.05.2026 11:00

On May 17, 2026, Grafana Labs said an unauthorized attacker had downloaded its codebase after accessing the firm's GitHub environment, and the company later said additional internal operational information and business contact names and email addresses were taken from its GitHub repositories; Grafana Labs said there was no indication that customer production systems or the Grafana Cloud platform were compromised.

OpenAI launches Daybreak cybersecurity initiative for AI-powered vulnerability detection and patch validation

Security Tool/Service
First: 12.05.2026 09:55 Last: 12.05.2026 09:55 Sources 1

About this happening: OpenAI's **Daybreak** launch adds an **AI-powered cybersecurity service** for **vulnerability detection** and **patch validation**, helping organizations fix flaws before attacker...

RoshniNaveenaS's account hit by network compromise

Incident
First: 29.04.2026 19:26 Last: 29.04.2026 19:26 Sources 1

About this happening: The **RoshniNaveenaS** account was **compromised**, enabling attackers to publish malicious **@cap-js** releases without provenance and putting downstream **npm** consumers at ris...

Indirect prompt injection payloads against AI agents reveal fraud, deletion, and secret-theft paths

Technical Analysis
First: 23.04.2026 12:30 Last: 23.04.2026 12:30 Sources 1

About this happening: **10** new **indirect prompt injection (IPI)** payloads show how web content poisoning can coerce **AI agents** into **financial fraud**, **data destruction**, and **API key theft...

Timeline

  1. 09.03.2026 01:35 1 articles · 2mo ago

    Issue #8904 starts prompt-injection chain against Cline

    Exploitation Observed

    An attacker created GitHub Issue #8904 in Cline with a title that looked like a performance report but contained an embedded instruction to install a package from a specific GitHub repository, beginning a prompt-injection path against Cline's AI-powered issue triage workflow.

    Show sources
  2. 09.03.2026 01:35 2 articles · 2mo ago

    Cline compromise disclosed with rogue OpenClaw deployment

    Initial Disclosure

    Cline's compromise was publicly described as a prompt-injection supply-chain attack that used additional vulnerabilities to push a malicious package into the nightly release workflow, resulting in thousands of systems receiving a rogue OpenClaw instance with full system access without consent.

    Show sources