AI Risk Wire

Cases · Developer or organisation: Anthropic · 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
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropicminor · earliest source 2026-08-05
security breachminor2026-08-05
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

Showing 1–3 of 3. Or take the JSON.