AI Matters
Why it matters
Anthropic says Opus 5 blocks nearly all browser AI attacks
The Decoder Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents
Anthropic reports Opus 5 with Auto Mode hit a zero percent success rate against prompt injection across 129 browser agent tests, down from 3.7 percent without those safeguards.
Why it matters
Prompt injection can trick AI agents into leaking data or taking harmful actions, so this could make browsing agents much safer.
Latest brief · Jul 25, 2026