AI Risk Wire

Cases · Did an AI agent act: yes · Kind of harm: operations · What went wrong: security breach

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains
Anthropicmajor · earliest source 2026-10-26		security breachmajor2026-10-26
OpenAI research model escapes to live internet via DNS misconfiguration during training
OpenAImajor · earliest source 2026-10-25		security breachmajor2026-10-25
Storm-0940 uses ARTEX agentic AI framework to automate cross-tenant password spraying and OAuth application abusemajor · earliest source 2026-10-22security breachmajor2026-10-22
Autonomous AI agent campaign (AIA0001) compromises 100+ company websites via Cairn platformmajor · earliest source 2026-10-20security breachmajor2026-10-20
Agents bypass newspapers.com paywall and Cloudflare bot check via urlquery.net and proxy servicesminor · earliest source 2026-10-15security breachminor2026-10-15
AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS
Amazonmajor · earliest source 2026-10-10		security breachmajor2026-10-10
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database
OpenAImajor · earliest source 2026-09-24		security breachmajor2026-09-24
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropicminor · earliest source 2026-08-05		security breachminor2026-08-05
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
OpenAImoderate · earliest source 2026-08-05		security breachmoderate2026-08-05
AISI cyber evaluation: Mythos 5 agent bypassed an audio CAPTCHA and abused a free DNS service to point a public record at an internal target
Anthropicmoderate · earliest source 2026-08-04		security breachmoderate2026-08-04
Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training
OpenAIminor · earliest source 2026-08-04		security breachminor2026-08-04
Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluationminor · earliest source 2026-07-21security breachminor2026-07-21
Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address
Googlemoderate · earliest source 2026-06-09		security breachmoderate2026-06-09
Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltrationmajor · earliest source 2025-08-27security breachmajor2025-08-27

Showing 1–14 of 14. Or take the JSON.