Tag: AI security

Showing 1-3 of 3

Jun 24, 20266 min readModel Release BriefIntermediate

Anthropic’s Mythos AI reportedly breached nearly all NSA classified systems during red-team test

Tom's Hardware reports Mythos AI reportedly breached 'almost all' NSA classified systems within hours during a red-team test. Learn why teams should deny outbound egress and rotate keys.

Anthropic Mythos AI security red team NSA

+3 more

NewsUnited Kingdom

Open

Jun 05, 20267 min readModel Release BriefIntermediate

Instagram's AI support chatbot exploited to change account recovery emails; Meta says issue fixed

Meta says it fixed a bug where Instagram's AI support chatbot could be tricked into changing account recovery emails, a method social posts tie to recent high-profile takeovers.

instagram meta ai-security chatbot account-takeover

+3 more

incident-response data-protection bbc

NewsFrance

Open

Apr 07, 20267 min readAgent PlaybookIntermediate

HiddenLayer 2026 report: autonomous agents widen AI runtime attack surface and account for roughly 1 in 8 breaches

HiddenLayer's 2026 AI Threat Landscape shows autonomous agents widen the runtime attack surface and account for ~1-in-8 AI breaches. Quick fixes: allowlist, ephemeral tokens, kill switch.

HiddenLayer AI security agentic AI autonomous agents threat landscape

+2 more

infosec security controls