LIVE FEED
FIRST LOOK OpenAI Expands ChatGPT Into Family and Caregiver Households // FIRST LOOK Iroh Launches Mesh LLM for Distributed AI Across Peer Nodes // HIGH HalluSquatting Exploits AI Hallucinations for Botnet RCE // CRITICAL OpenClaw AI Assistant Flaws Enable WhatsApp-to-Host RCE // FIRST LOOK Netwrix Analysis: AI Agents Widen the Non-Human Identity Gap // FIRST LOOK Ghostcommit PoC Embeds Prompt Injection in PNG to Steal Repo Secrets // FIRST LOOK Microsoft MDASH Brings AI-Powered Windows Vulnerability Discovery // FIRST LOOK FableCut Ships AI-Drivable Browser Video Editor via MCP and REST // FIRST LOOK AI Agents Emerge as a New Identity Class Orgs Must Secure // HIGH CVE-2026-12958: GhostApproval Symlink Attack on Coding Agents //
MODEL-THEFT

Model-Theft

3 reports
All LLM Security Agentic AI Industry News Research Supply Chain Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Model Theft Data Poisoning AI Security Tools Security Operations
Anthropic Mythos Model Theft: China-Linked Access

Anthropic Mythos Model Theft: China-Linked Access

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 8.5 The Verge AI

The White House reportedly believes a China-linked group accessed Anthropic's Mythos AI model, prompting export restrictions on the technology. If confirmed, the breach represents a significant national security threat, as adversaries could exploit the model directly or use knowledge distillation to replicate its capabilities. Separately, reports of jailbreak vulnerabilities in Mythos and Fable compound concerns about unauthorised access to frontier AI systems.

Qwen 3.5-397B Model Theft: Rio's LLM Exposed as Rebranded Clone

Qwen 3.5-397B Model Theft: Rio's LLM Exposed as Rebranded Clone

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.8 HN AI Security

Researchers have demonstrated that Rio de Janeiro's publicly presented 'homegrown' 397B language model is not an original creation but an undisclosed element-wise weight merge of the Nex-N2_pro model and Qwen3.5-397B-A17B. The finding was established through two independent methods: identity probing showing the model identifies as 'Nex' 79% of the time, and tensor-level statistical analysis confirming a consistent 0.6/0.4 blend across all 60 layers. This constitutes a model theft and supply chain integrity violation, with additional implications for public trust in government AI procurement and IP attribution.

Claude Source Code Leak Reveals AI Supply Chain Risk

Claude Source Code Leak Reveals AI Supply Chain Risk

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 Dark Reading

A reported source code leak affecting Claude, Anthropic's large language model, underscores systemic weaknesses in AI software supply chains and the absence of robust oversight mechanisms at critical development and distribution layers. The incident highlights how proprietary model code, training pipelines, and system prompts can become high-value targets for adversarial actors seeking to enable model theft, backdoor insertion, or competitive intelligence gathering. This event serves as a broader warning about treating AI development infrastructure with the same rigor applied to other critical systems.

◉ 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.