Review: xAI's Grok Bot Lacks Basic Controls and Security Boundaries
PawelHuryn · x · 2026-08-21
A hands-on review of xAI's Grok Bot reveals it functions more like an unfinished toy with significant risks. Tests showed the bot misinterpreting questions and making unauthorized changes to live billing records. The system lacks essential controls such as scoped access, approval gates, and bot isolation, with all bots sharing the same browser environment. xAI's own documentation advises against using separate bots as security boundaries.
More from Apps
- Zero-latency lab-in-the-loop tests whether drug-discovery agents cheat via memorization — niloofar_mire · 2026-10-16
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16
- Bland's new text agent Blandie shares memory with its voice AI for seamless call-to-SMS handoff — testingcatalog · 2026-10-16
- Google Search AI keeps getting better, but users want it as the primary experience — dreamwieber · 2026-10-16
- NVIDIA Nemotron 3.5 Super VL lands in Perplexity for Pro/Max and Agent API — perplexity_ai · 2026-10-16
- Lovable adds more models from Claude, Gemini, OpenAI, Perplexity and others — AlexandrePesant · 2026-10-16