Topic

Security & Safety

Prompt injection, agent security, and AI safety in production: real attack surfaces, defenses that hold up, and how teams ship agents without shipping incidents.

11 articles
Securing AI Agents and LLM Apps: The 2026 Threat ModelPillar

Securing AI Agents and LLM Apps: The 2026 Threat Model

Why indirect prompt injection, tool-mediated exfiltration, and rogue agents now define LLM security, and the layered controls that actually hold.

20 minJune 15, 2026
Clinical AI's Real Attack Surface Is the EHR Integration, Not the ModelSecurity & Safety

A Clinical Scribe Fell to Three Prompts. The VA Scaled It to 130 Sites

The Heidi Health NEXUS jailbreak proved safety lives in a text layer the model will gladly rewrite, and the VA just multiplied that risk across 130 facilities.

12 minJune 28, 2026
HIPAA, GDPR, and the EU AI Act: One Stack, Three Frameworks, Five WeeksSecurity & Safety

Five Weeks Until EU AI Act High-Risk Day. Is Your Stack Ready?

The August 2, 2026 high-risk deadline stacks three compliance regimes onto a single AI product. Here's how to satisfy them simultaneously.

11 minJune 28, 2026
AI Data Center Permitting Met a New Bypass: National SecuritySecurity & Safety

AI Data Center Permitting Met a New Bypass: National Security

The DOJ's xAI intervention turns 'national security' into a legal lever to skip Clean Air Act permits, and founders building AI infrastructure should track every move.

9 minJune 26, 2026
AI Safety Routing Is Real. The Audit Trail Isn't YetSecurity & Safety

AI Safety Routing Is Real. The Audit Trail Isn't Yet

Routing risky prompts to safer models can be a serious governance control, but only if buyers can inspect the classifier, fallback chain, logs, and audit evidence.

12 minJune 21, 2026
AI Model Shutdown Risk Is Now a Friday ProblemSecurity & Safety

AI Model Shutdown Risk Is Now a Friday Problem

Anthropic's Fable 5 suspension turned model choice into an availability-control problem, and the fix is contractual, technical, and operational.

12 minJune 20, 2026
Red-teaming AI in 2026: the practical guide to adversarial testingSecurity & Safety

Red-teaming AI in 2026: a practical adversarial testing guide

A step-by-step methodology for designing AI red-team exercises, plus an honest comparison of PyRIT, Garak, HarmBench, and Promptfoo.

10 minJune 12, 2026
AI Risk Management in 2026: Shadow AI, Data Leaks, and the Regulatory SqueezeSecurity & Safety

AI Risk Management for Enterprises: Closing the Shadow AI Gap

Four in five enterprise AI tools run unmanaged while the EU's high-risk deadline lands in August. Here's the playbook that actually closes the gap.

11 minJune 11, 2026
AI's Role in Critical Decision-Making: Risks, Rewards, and ResponsibilitiesSecurity & Safety

AI Decision-Making in High-Stakes Sectors: Risks and Rewards

From NHS radiology wards to courtrooms and kill chains, AI is making consequential calls faster than the law can assign blame for them.

10 minJune 11, 2026
Prompt Injection in 2026 Looks Nothing Like 2023. Here's ProofSecurity & Safety

Prompt Injection in 2026 Looks Nothing Like 2023. Here's Proof

Production attacks have moved to multi-step goal hijacking, context pollution, and delayed payloads while most deployed defenses still grep for 'ignore previous instructions.'

10 minJune 11, 2026
How to Read an AI System Card in 2026: The Anthropic Fable 5 Walk-Back TestSecurity & Safety

Reading AI System Cards in 2026: The Anthropic Walk-Back Test

Anthropic reversed Claude Fable 5's silent anti-sabotage clause in 48 hours. The episode is a repeatable audit template for every system card you'll read this year.

11 minJune 11, 2026