Research

GenAI Security Risks: OWASP Updates LLM Top 10 Framework

ATLAS OWASP MEDIUM ▲ 7.2 Dark Reading Apr 14, 2026

OWASP has updated its GenAI Security Project to formally recognise 21 generative AI risks, releasing a new tools matrix to help organisations structure their defences. The update notably distinguishes between securing traditional GenAI systems and the emerging attack surface presented by agentic AI architectures. This guidance represents a significant standards-level acknowledgement that agentic AI requires its own dedicated security posture.

Google Vertex AI Over-Privilege Enables Data Exfiltration

ATLAS OWASP HIGH ▲ 8.5 Dark Reading Apr 13, 2026

Palo Alto Networks researchers have identified over-privilege vulnerabilities in Google's Vertex AI platform, demonstrating how malicious actors could exploit AI agents to exfiltrate sensitive data and pivot into restricted cloud infrastructure. The findings highlight systemic risks in agentic AI deployments where excessive permissions granted to AI workloads expand the attack surface beyond traditional cloud security boundaries. This research underscores the growing urgency around securing AI agent permissions and enforcing least-privilege principles in enterprise ML platforms.

SWE-bench, WebArena Exploited via Environmental Manipulation

ATLAS OWASP CRITICAL ▲ 9.2 HN AI Security Apr 11, 2026

Researchers at UC Berkeley demonstrated that every major AI agent benchmark — including SWE-bench, WebArena, OSWorld, and others — can be fully exploited to achieve near-perfect scores without solving a single task, using trivial environmental manipulation rather than genuine capability. The attacks include pytest hook injection, config file leakage, DOM manipulation, and reward component bypassing, with zero LLM calls required in most cases. This represents a systemic integrity failure in the evaluation infrastructure underpinning AI deployment decisions across industry and research.

US summons bank bosses over cyber risks from Anthropic's latest AI model

ATLAS OWASP CRITICAL ▲ 8.5 HN AI Security Apr 10, 2026

The US Treasury convened major bank executives to discuss cybersecurity risks posed by Anthropic's unreleased Claude Mythos model, which the company claims has surpassed nearly all human experts at finding and exploiting software vulnerabilities. A code leak prompted Anthropic to publicly acknowledge the model's unprecedented offensive cyber capability, raising systemic financial sector risk concerns. The meeting signals growing regulatory awareness of AI-enabled cyber threats to critical financial infrastructure.

Anthropic Mythos AI Autonomously Discovers Zero-Day Exploits

ATLAS OWASP HIGH ▲ 8.2 Dark Reading Apr 10, 2026

Anthropic has released a preview of 'Mythos,' an AI model reportedly capable of autonomously discovering and exploiting critical zero-day vulnerabilities, raising significant dual-use concerns. While Anthropic claims the model ships with access controls, the security community is scrutinising whether those safeguards are sufficient to prevent misuse by malicious actors. The development represents a pivotal moment in the arms race between offensive AI capabilities and defensive governance frameworks.