Grok Bot now detects hidden prompt injections, warns users and refuses to follow them
XFreeze · x · 2026-11-11
According to XFreeze on X, Grok Bot now surfaces a warning when a page or message tries to inject hidden text into your chat, and refuses to follow those instructions.
Example: ask about a store's return policy and if the page sneaks in commands aimed at agents, Grok Bot answers your actual question while flagging what it found. The poster frames it as a simple but important security habit built directly into the product.
More from Models
- Krafton open-sources Raon-1 nano, a 1.5B on-device LLM distilled from MoE — DimitrisPapail · 2026-11-11
- Do typos discomfort LLMs? Tokenization quirk sparks debate — menhguin · 2026-11-11
- MiniMax H3 hits 100 days open-source: 1,472 derivative models, 148M+ downloads — linoy_tsaban · 2026-11-11
- Meituan's LongCat-2.5 trends on Hugging Face as MoE multimodal model — meituan-longcat · 2026-11-11
- Fable 5.2 hands-on: great at well-defined hard problems, best since GPT 6 Astra — rachittshah · 2026-11-11
- The next AI vendor lock-in won't be the model API, it'll be the harness — Arindam_1729 · 2026-11-11