Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents
Opus 5 combined with Auto Mode hits a zero percent prompt injection success rate for browser agents across 129 test scenarios. Without those extra protection layers, the rate is 3.7 percent. If these numbers hold up in practice, Anthropic may have cracked one of the biggest security problems facing AI agents that operate in browsers. The article Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents appeared first on The Decoder .
Record details
Published: 25 July 2026
Source: The Decoder
Category: News
Topics: Agents & autonomy
Retrieved: 26 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted
The Decoder · 5 August 2026
SpaceXAI's Grok 4.6 matches OpenAI's best model and undercuts it on price
The Decoder · 12 August 2026
Gemini 3.7 Flash lands with coding gains and undercuts its three-week-old predecessor's price by 50%
The Decoder · 13 August 2026
US reportedly favors selective bans over blanket restrictions on Chinese open weight models citing security concerns
The Decoder · 26 July 2026
Kimi K3 trails frontier US models by a wide margin on cyber exploits, and distillation may explain why
The Decoder · 24 July 2026
Anthropic's $1.5B piracy settlement with book authors is a record loss that hands AI labs their biggest legal win
The Decoder · 22 July 2026
How to cite this record
ethics.ai (25 July 2026), “Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents,” evidence record 13567, https://ethics.ai/record/13567 (originally published by The Decoder).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.