I security for December 3, 2025 centers on new NSA/CISA guidance for safely integrating AI into OT, SandboxAQ’s launch of an AI security posture platform for shadow AI, research showing poetic prompts can jailbreak major models, Experian’s forecast naming AI as the top breach driver for 2026, and TÜV SÜD’s move to formalize AI penetration testing using NIST, OWASP, and MITRE ATLAS.
AI security on Dec 2 centers on a serious Codex CLI command-injection flaw, new data showing layered AI defenses still buckle under targeted attacks, Anthropic’s agents successfully exploiting real DeFi contracts, Android zero-days hitting AI-enabled mobile endpoints, and a major investment push into explainable AI-driven investigations for national security
Over the past five days, malicious and “dark” LLMs have lowered the bar for cybercrime, HashJack has exposed a new AI-browser injection vector, Olymp Loader continues to evolve as a stealthy MaaS platform, Anthropic’s Claude Opus 4.5 boosts agent capabilities amid ongoing safety concerns, and new CVEs and identity hardening moves remind defenders that AI security is inseparable from solid infrastructure and IAM hygiene.
“HashJack” exposes a new class of AI-browser prompt injection, malicious underground LLMs accelerate attacker automation, and a new fully-undetectable MaaS loader raises baseline threat levels.
LLMs demonstrate autonomous-malware capabilities, Trend Micro launches a dedicated AI-security platform, Microsoft and GitHub preview AI auto-remediation for vulnerabilities, and new updates emerge on Fluent Bit logging flaws and DeepSeek-R1 model risks.
Second-order prompt injection in ServiceNow’s Now Assist, a new vLLM RCE, DeepSeek-R1’s insecure code bias, adversarial poetry jailbreaks, and fresh field lessons on securing GenAI all highlight how AI infrastructure, models, and safety controls are being stress tested in the real world.
AI agents amplify identity risk; OAuth tokens exploited in SaaS/AI integrations; U.S. charges GPU smuggling scheme; EU simplifies AI-cyber regulation.
U.S. approves export of advanced AI chips to Middle East; House passes legislation to monitor terrorist use of generative AI; new cybersecurity training approaches emphasise AI-literacy.
Deepfakes and AI-crime surge in Ohio; Black Kite launches AI Agent for third-party risk; exploit targets AI orchestration framework; global AI-in-cybersecurity market forecast hits $154.8 bn.
SentinelOne releases new AWS integrations to secure GenAI workloads, Google patches an actively exploited Chrome zero-day, an Imunify AI-Bolit flaw threatens hosting environments, and state-level AI regulation surges ahead of federal policy.
TECHMANIACS.com 