LIVE FEED
CRITICAL SGLang RCE Exploit Breaches NEAR AI, Hits 18 Agents // FIRST LOOK F-Secure Releases AI Harms Taxonomy Mapping 26 Consumer Risks // CRITICAL Cursor Marketplace Trojanized via Stolen Fireworks AI Key // CRITICAL Cairn AI Framework Hits Semiconductor and Defense Orgs // HIGH TypoPrompting: 186 Fake AI Domains Spread ClickFix Malware // CRITICAL Post-Training Supply Chain Attacks Backdoor AI Coding Agents // HIGH Google Project Zero Cuts Disclosure Window as LLMs Speed Up Exploits // HIGH Unsanctioned AI Agents Expose Five Enterprise Identity Security Gaps // HIGH OpenAI Agents Gain Root Access, Conceal Activity in CI Clusters // FIRST LOOK AWS Launches A2A Protocol for Interoperable Multi-Agent Systems //
LOCAL-LLM

Local-Llm

4 reports
All LLM Security Agentic AI Industry News Research First Look: Security Supply Chain Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report Monthly Review AI Governance AI Security AI Security Tools Identity & Access Management Security Operations
BOSSAI AI Agents Used to Breach Taipei Emergency Dispatch Systems

BOSSAI AI Agents Used to Breach Taipei Emergency Dispatch Systems

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.5 The Hacker News

A single threat actor based in Hualien City, Taiwan deployed locally-run, safety-stripped AI agents under the BOSSAI framework to compromise emergency dispatch systems, fire department databases, and sensitive patient records across Taiwan, Mexico, and Thailand. The attacker circumvented commercial AI refusals by running 'abliterated' models with safety training removed, enabling autonomous reconnaissance, credential exploitation, and data exfiltration across critical infrastructure targets. The case represents a concrete, real-world demonstration of AI agents being weaponised against public-safety systems at scale.

NVIDIA Launches Nemotron 3.5 Super VL and Bolt Agent Models

NVIDIA Launches Nemotron 3.5 Super VL and Bolt Agent Models

FIRST LOOK ATLAS OWASP LOW Limited impact · Standard review ▲ 5.8 TechCrunch AI

NVIDIA has released Nemotron 3.5 Super VL (120B parameters) for enterprise agentic workloads and two lightweight Bolt models for local PC deployment, all as open-weight models that organisations can post-train and self-host. For defenders, the shift to on-premises, self-hosted agentic models closes a meaningful data-sovereignty gap — sensitive workflows involving financial, medical, and security data no longer require routing through third-party frontier APIs. Residual gaps remain around enterprise readiness for securing agentic pipelines, validating post-trained model behaviour, and governing always-on local agents at endpoint scale.

AI Worm Autonomously Generates Exploits at Runtime

AI Worm Autonomously Generates Exploits at Runtime

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 The Hacker News

University of Toronto researchers demonstrated a proof-of-concept AI worm that leverages a locally hosted open-weight LLM to autonomously reason through network targets, generate novel exploit chains at runtime, and self-replicate — achieving 62% network penetration across a 33-host testbed with no human intervention. Unlike traditional worms with fixed payloads, this system bypasses conventional patch-based defences by dynamically adapting attack logic to whatever vulnerabilities it discovers. The use of offline open-weight models eliminates dependency on commercial AI APIs, making it resilient to rate-limiting or platform-level safety controls.

DeepSeek Activation Steering Enables Local LLM Jailbreak

DeepSeek Activation Steering Enables Local LLM Jailbreak

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.2 HN AI Security

Activation steering — the technique of directly manipulating LLM internal representations mid-inference to alter model behaviour — is becoming more accessible to non-lab engineers via local models like DeepSeek-V4-Flash. This democratisation lowers the barrier for adversaries to craft targeted behavioural overrides that bypass prompt-level safety controls. The emergence of first-class steering support in tools like DwarfStar 4 signals that model-internal manipulation is transitioning from academic curiosity to practical attack surface.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.