Application security , AI/ML , Generative AI , SOC AI-driven attacks target governments, cloud agents, supply chains April 23, 2026 Share By OWASP GenAI Security Project Team , By Staff report (Adobe Stock) A new OWASP report on GenAI security incidents shows cyberattacks rapidly evolving from theoretical risks to real-world exploitation, with attackers increasingly leveraging AI to scale operations and target critical systems. Among the most significant cases is a breach of Mexican government agencies , where attackers used AI tools such as Anthropic’s Claude and ChatGPT to automate reconnaissance and exploit development. The campaign exposed roughly 150 GB of sensitive tax and voter data, demonstrating how AI can compress the time and effort required to execute large-scale intrusions. Researchers said the attack expanded across multiple agencies, highlighting the growing risk to public-sector systems as AI accelerates attack workflows. Risks in cloud-based AI infrastructure In one case, researchers uncovered a “Double Agent” scenario in Google Cloud’s Vertex AI platform , where an overprivileged agent could abuse default permissions to access sensitive data, extract credentials, and pivot into broader cloud resources. The findings underscore concerns around identity and privilege management in agentic systems, particularly as organizations rely more heavily on managed AI services with complex trust boundaries. Supply chain vulnerabilities are another growing concern A breach involving AI data vendor Mercor , linked to compromised versions of the LiteLLM tool , raised fears that proprietary training data workflows and contractor information across major AI labs could have been exposed. The incident prompted Meta to pause work with the vendor and highlighted how third-party dependencies in AI ecosystems can introduce cascading risks across multiple organizations. Across these incidents, OWASP researchers emphasize a broader shift in the threat landscape. Rather than focusing solely on model-level vulnerabilities, attackers are exploiting weaknesses in identity, orchestration layers, and interconnected supply chains. Many of these risks stem from misconfigurations, excessive permissions, and design flaws rather than traditional software bugs. The report concluded that securing AI systems will require a more holistic approach, combining system-level controls, stronger identity governance, and tighter oversight of third-party dependencies as AI becomes a central component of both enterprise and government operations. Read about more trends from the OWASP GenAI roundup of incidents from the first quarter of 2026. OWASP GenAI Security Project Team Staff report Related Application security Ofcom investigates Telegram for child abuse material sharing SC Staff April 22, 2026 The investigation was prompted by evidence from the Canadian Centre for Child Protection and Ofcom's own assessment, which indicated the presence and dissemination of CSAM on Telegram. Network Security The browser is the battlefield: Why security must be where work happens Paul Wagenseil April 22, 2026 The browser is no longer just a tool. It's the primary battleground of enterprise security. AI/ML Firefox report offers early insight into Claude Mythos AI model Steve Zurier April 22, 2026 AI model finds hundreds of bugs in Firefox, boosting defense — but also lowering barriers for attackers. Related Events Cybercast Protecting Application User Data for Better Privacy, Governance, and Compliance On-Demand Event Cybercast The Next Evolution of Application Security: AI- Accelerated DevSecOps On-Demand Event Cybercast Scaling secure software in the age of AI: Turning intelligence into action On-Demand Event Get daily email updates SC Media's daily must-read of the most current and pressing daily news Business Email By clicking the Subscribe button below, you agree to SC Media Terms of Use and Privacy Policy . Subscribe Related Terms Algorithm Blue Team Cache Cramming Client Cold Warm Hot Disaster Recovery Site Common Gateway Interface (CGI) Countermeasure Cron DLL Injection Daemon You can skip this ad in 5 seconds