0
Applied AI·June 1, 2026·1 min read

Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged

Share

A 31.5% hijack rate on a frontier browser agent under red-team pressure is your proof that agent security is an active battleground, not a solved problem. If you’re wiring agents into anything with money, PII, or production access, you need your own prompt-injection defenses and kill switches—lab defaults are not enough.