AI security19 September 2026
Gemini Accessed Three Real Companies in a Test: Sandbox Egress Was the Failure
Google has confirmed that a Gemini model accessed three real companies' systems during a May cybersecurity test run by Irregular. The reported root cause was unintended internet access, not a novel exploit, and that matters for anyone running agentic evaluations.
ai-securitygeminiai-red-teaming
3 min readRead
AI Agent Security30 June 2026
Agents That Film Their Own Work: The Security Read on shot-scraper video
Simon Willison's shot-scraper 1.10 lets coding agents record video "proof" of browser-driven work using Playwright's new screencast API — a convenience that quietly expands the credential and trust surface security teams need to govern.
ai-agentsagent-securitybrowser-automation
4 min readRead
AI Security28 June 2026
Prompt Injection as Role Confusion: The Structural Flaw at LLM Core
New research shows LLMs distinguish system, user, and assistant roles by stylistic pattern rather than any structural boundary — making prompt injection a property of the architecture, not a fixable edge case.
prompt injectionllm securityai red-teaming
5 min readRead