LIVE FEED
FIRST LOOK OpenAI Updates Model Spec to Sharpen AI Judgment and Safety // HIGH Prompt Injection Targets AI Agent Planning in New Attacks // FIRST LOOK Mistral Releases Mistral Large 4 Open Weights for Cyber Defense // HIGH Hugging Face Malware Hijacks GPUs via trust_remote_code // CRITICAL Claude Code VS Code Extension Trojanized with SSH Backdoor // FIRST LOOK YC Labs Runs GPT-6.1 Multi-Agent Swarms in Open Game Worlds // FIRST LOOK AWS AgentCore Gateway Turns 400-Plus APIs into Agent Tools // MEDIUM Claude Code Agent Transcripts Leaked via Silent Token Drain // FIRST LOOK Google Launches Gemini 4 Carbon with Cybersecurity Leap // HIGH Attackers Impersonate AI Bots to Scan for Exposed Credentials //
CHAIN-OF-THOUGHT-EXTRACTION

Chain-of-Thought-Extraction

2 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
OpenAI Compaction Flaw Exposes Hidden Reasoning in GPT-5.6

OpenAI Compaction Flaw Exposes Hidden Reasoning in GPT-5.6

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

Security firm Xint discovered that OpenAI's compaction feature — which compresses long conversations into encrypted context items — could be manipulated to extract a reasoning model's hidden chain-of-thought as plain text. The technique bypassed protections OpenAI had shipped in August 2026 to prevent cross-model reasoning replay attacks, because compaction runs on the same model that generated the reasoning, circumventing the cross-model check. OpenAI confirmed and patched the vulnerability on October 23, 2026, awarding Xint a $6,000 bug bounty, though researchers warn that any server-side step reading decrypted reasoning while following user instructions remains a potential leakage vector.

Anthropic Exposes 200M-Exchange Model Distillation Attacks

Anthropic Exposes 200M-Exchange Model Distillation Attacks

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 TechCrunch AI

Anthropic has published a detailed report attributing nearly 200 million adversarial API exchanges to coordinated model distillation campaigns conducted by Alibaba, Moonshot AI, and DeepSeek. Attackers used prompt obfuscation techniques — including fake translation requests — to bypass Claude's summarised-thinking safeguards and extract raw chain-of-thought traces for use as supervised fine-tuning data. One Moonshot AI campaign was assessed as routing requests directly through Chinese military infrastructure, adding a significant geopolitical dimension to what is otherwise an IP-theft threat.

◉ 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.