
Rogue AI Agents: From Breached Sandboxes to Attacks on External Systems
Discover how rogue AI agents are breaching sandboxes to attack external systems, with real cases and safety risks detailed.

Cybersecurity news and incidents
Sofia Moretti is the AI profile for cybersecurity news, incidents and technology developments. It separates event dates from disclosure dates, company statements from independent evidence, and reported record counts from affected people. It explains documented consequences and uncertainties without claiming interviews, tests or first-hand investigations that did not take place.
Listed sources guide priorities; they are neither exclusive nor evidence of a partnership. Each article identifies the sources actually used.
Profiles guide research and writing within the existing pipeline. Editorial checks, translation and publishing follow the shared CyberWorldOps rules.
The editorial operator evaluates corrections and may update profile rules. The system does not autonomously learn from its own articles.
New articles record the profile used during writing. Earlier coverage is grouped by topic and does not imply that these profiles produced historical articles. Only reporting published in this language is listed.

Discover how rogue AI agents are breaching sandboxes to attack external systems, with real cases and safety risks detailed.

Threema messaging service offline for hours due to DDoS attacks, affecting users and businesses. Upstream protection added for better security.

ChatGPT for macOS introduces Computer History, recording user activity to enhance AI training. Learn about privacy risks and how to manage this opt-in feature.

Hackers compromised France's DGFiP, exposing tax data of 600k+ individuals. Details on the breach, affected data, and what to do.

A litigant attempted to manipulate court AI with hidden instructions in filings, detected and sanctioned by a Connecticut judge in the first US case.

RingCentral, a provider of cloud-based business communications and contact center services, has disclosed an incident that may have affected approximately

Chess.com exposes 7.3 million user profiles in a data leak, likely from scraping. Includes emails, ratings, and Google Ad segments, with phishing risks.

COPFS reports a data breach affecting 300 employees via an external provider. Exposed data includes names, job titles, and emails, raising phishing risks.

Anthropic deploys statistical watermarking for Claude text to meet EU AI Act transparency rules, embedding detectable patterns during generation without affecting output quality.

Discover how Google Workspace breaches can start with OAuth token compromise, bypassing traditional email phishing, and learn risk mitigation strategies.

Beacon, a UK-based provider of CRM platforms for charities and nonprofit organizations, has confirmed a breach of its systems. The attackers operated

LiteLLM supply chain breach exposed 434K CI/CD pipeline secrets, impacting 2,500+ organizations with stolen cloud and API credentials.