LIVE FEED
FIRST LOOK OpenAI Releases Astra Cybersecurity Evals and Safeguard Controls // FIRST LOOK OpenAI Pauses Astra Model Over Critical Cybersecurity Threshold // CRITICAL OpenAI Agents Exploit Artifactory RCE in Hugging Face Attack // FIRST LOOK Cloudflare Launches Kitesurf, a Cloud Browser Built for AI Agents // FIRST LOOK PortSwigger HTTP Terminator Ships AI-Driven Desync Research // CRITICAL CVE-2026-12537: Gemini CLI RCE and Claude Code Secret Leak // HIGH Atlassian Rovo Prompt Injection Leaks Jira Data to Attackers // CRITICAL Claude and ChatGPT Hijacked via Zero-Click Prompt Injection // HIGH ChatGPT Sandbox C2 Attack Demonstrated at Black Hat 2026 // HIGH Meta AI Hacks External Systems in Cybersecurity Test //
GOOGLE-DEEPMIND

Google-Deepmind

3 reports
All LLM Security Agentic AI Industry News Supply Chain Research Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Model Theft Data Poisoning AI Governance AI Security AI Security Tools Deep Signal Identity & Access Management Intelligence Report Security Operations
Google Gemini API Adds Hooks, Budget Controls, and 3.6 Flash Agents

Google Gemini API Adds Hooks, Budget Controls, and 3.6 Flash Agents

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.2 Google DeepMind Blog

Google has updated its Managed Agents in the Gemini API with Gemini 3.6 Flash as the new default model, environment hooks that allow interception of tool calls, budget controls, scheduled triggers, and free tier access. The introduction of environment hooks — which can block, lint, or audit tool calls inside the agent sandbox — creates a new interception layer that, if misconfigured or bypassed, could allow malicious tool calls to slip through undetected. Defenders deploying these agents must treat hooks as a critical trust boundary and scrutinise scheduled triggers and budget controls as potential abuse vectors for persistent, low-cost autonomous operations.

Google DeepMind Releases AI Agent Attack Taxonomy

Google DeepMind Releases AI Agent Attack Taxonomy

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.7 SecurityWeek

Google DeepMind researchers have released a structured taxonomy categorising adversarial attacks against autonomous AI agents into six classes — content injection, semantic manipulation, cognitive state poisoning, behavioural control, systemic, and human-in-the-loop traps — formalising an emerging threat model for agentic AI systems. For defenders, this framework codifies attack paths that exploit the agent's inability to distinguish trusted instructions from attacker-controlled data ingested from web pages, emails, documents, and tool outputs. NIST evaluation data cited in the research shows malicious instruction injection succeeded in 57% of tested agent hijacking scenarios on average, underscoring that these are active, high-yield attack vectors rather than theoretical concerns.

Model Extraction Attacks Surge: Google GTIG Q4 Report

Model Extraction Attacks Surge: Google GTIG Q4 Report

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.5 Mandiant Blog

Google Threat Intelligence Group's Q4 2025 AI Threat Tracker documents a meaningful escalation in adversarial AI misuse, including a surge in model extraction (distillation) attacks, nation-state operationalisation of LLMs for phishing and reconnaissance, and the emergence of AI-integrated malware families such as HONESTCUE that leverage Gemini's API. While no breakthrough capabilities have been observed from APT actors, the integration of agentic AI for tooling development signals a maturing threat landscape. Defenders should prioritise monitoring for model extraction activity, API abuse, and AI-augmented social engineering campaigns.

◉ 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.