prompt injection

OpenAI's new GPT-6 Astra model shows major improvements in hallucination rates and jailbreak resistance over predecessor GPT-5.6 Sol, according to OpenAI's system card. However, indirect prompt injection attacks hidden in documents still succeed 8.5% of the time in external testing by Gray Swan, down from 27% but still above rival Claude Opus 5's 4.8% rate.

Anthropic is embedding a dedicated browser into Claude Cowork's desktop app, opening in a side panel whenever a task requires web access. The browser is isolated from the user's own tabs, bookmarks, and passwords, and rolls out this week to Pro, Max, Team, and Enterprise plans.

Anthropic will make auto mode the default setting for new Claude Code sessions on Pro, Max, and Team plans starting August 14, 2026. The company cites a 1,053-person study showing auto mode blocked 89% of harmful actions compared to 13.6% for human reviewers, plus a third-party test claiming zero successful prompt injections out of 720 attempts.

Google's agentic AI assistant Spark now integrates with Chrome, letting it use logged-in accounts and saved passwords to handle tasks like researching flights and scheduling apartment viewings. The feature is rolling out in the US now, alongside expanded Spark access for Google AI Pro subscribers in over 160 countries.

Anthropic's system card for Claude Opus 5 reports a 0% prompt injection success rate across 129 browser agent test scenarios when Auto Mode is enabled. On Gray Swan's broader indirect prompt injection benchmark, Opus 5 posted a 2.0% attacker success rate after 15 attempts, the lowest among tested frontier models.