Analysis · curated 2 Aug 2026
Anthropic's Opus 5 Is Better at Resisting Prompt Injection - Schneier on Security
First reported schneier.com
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
Prompt injection robustness benchmarks give defenders concrete comparative data on how well deployed LLMs and agents resist attacker manipulation, informing model selection for agentic and browser-use deployments.
Schneier highlights results from Anthropic's Claude Opus 5 system card showing improved robustness on the indirect prompt injection (IPI) benchmark, reducing an attacker's success probability within 15 attempts from 5.5% (Opus 4.8) to 2.0%, and outperforming rival models like GPT 5.6 Sol (20.0%) and Muse Spark (16.5%). The post notes that while prompt injection is considered impossible to prevent in the general case, models are getting substantially better at blocking it in specific cases.