AI

Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents

Featured from AI & Machine Learning Desk

Anthropic's Opus 5 model, when combined with Auto Mode in products like Claude Cowork, achieved a zero percent prompt injection success rate across 129 browser

Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents

Key takeaways

  • Opus 5 combined with Auto Mode hits a zero percent prompt injection success rate for browser agents across 129 test scenarios.
  • Without Auto Mode protection layers, the Opus 5 prompt injection success rate is 3.7 percent.
  • Opus 5 leads the Gray Swan IPI benchmark with a 2.0 percent attacker success rate after 15 attempts.
  • Sonnet 5 performs better than standalone Opus 5 without Auto Mode, sitting at a 0.93 percent success rate.

Anthropic's Opus 5 model, when combined with Auto Mode in products like Claude Cowork, achieved a zero percent prompt injection success rate across 129 browser agent test scenarios. Auto Mode uses two defense layers: scanning incoming data for hidden instructions and blocking dangerous actions before execution. Without these layers, the Opus 5 injection rate is 3.7 percent, while Sonnet 5 sits at 0.93 percent. In general prompt injection tests by Gray Swan, Opus 5 led the benchmark with a 2.0 percent attacker success rate, outperforming Mythos 5 and Fable 5.

Watch the brief

By the numbers

0%
Prompt injection success rate across 129 test scenarios
3.7%
Opus 5 prompt injection success rate without Auto Mode
2.0%
Opus 5 attacker success rate on Gray Swan benchmark
0.93%
Sonnet 5 prompt injection success rate without Auto Mode

How it unfolded

  1. December OpenAI admits prompt injection may never be fully solved
  2. 2026-07-25 Anthropic system card reveals Opus 5 security test results

Turn stories like this into views

Ravenclip finds the AI news, makes the video, and posts it before attention moves on.

Start my channel

Source: The Decoder

Common questions

What happened with Opus 5?
Opus 5 combined with Auto Mode hits a zero percent prompt injection success rate for browser agents across 129 test scenarios.
Where can I read the original report?
Read the full report at the_decoder.

More in AI