6 casos · pág. 1/1
F5 Labs published its November 2025 AI Security Insights, drawn from the Comprehensive AI Security Index (CASI) and Agentic Resistance Scoring (ARS). Anthropic models took the whole top tier of the CASI leaderboard (Claude Haiku 4.5 at 95.89, Claude Sonnet 4.5 at 95.86, Claude Sonnet 4 at 95.33), while the GPT-5 family slipped, with GPT-5…
In August 2026, data centre operator CyrusOne was targeted in a ShinyHunters "pay or leak" extortion attempt. The group later published data allegedly stolen from the company, covering about 373k unique email addresses across records for users, sales leads and CyrusOne employees. The data is mostly corporate contact information, and also …
In January 2026, the company intelligence platform Crunchbase was targeted in a ShinyHunters "pay or leak" extortion attempt. Data allegedly stolen from the company was later published, covering about 560k unique email addresses, mostly belonging to leads and business contacts. Crunchbase subsequently confirmed that a threat actor had exf…
A SafeDep researcher describes an experiment that uses Gryph (an audit trail for AI coding agents) and TypeSafe AI's Jev model to separate a developer's normal agent activity from attacks. The article cites threats to agents such as Claude Code and Codex: the Mini Shai-Hulud worm commits Claude Code hooks into repositories, malicious npm …
F5 Labs published its March 2026 CASI Leaderboard update, which is now dominated by OpenAI and Anthropic. Z.ai's GLM-5 performs well on price and capability but has a weak security posture (CASI 37.56 vs 96.61 for Claude Opus 4.6 and 92.58 for GPT-5.2). The report also spotlights Sugar-Coated Poison (SCP), a multi-turn technique that grad…
The Wiz Customer Incident Response Team (CIRT) reports a growing number of intrusions in which an AI agent system ran the entire operation: finding entry points, harvesting credentials, pivoting across platforms and debugging its own scripts in real time. In one investigated case, the agent compromised a large multi-cloud organization (GC…
