{
  "id": 2393996,
  "title": "Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini",
  "url": "https://urgent.news/2026/08/21/encrypted-prompts-bypass-ai-safety-guardrails-in-grok-and-gemini",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-21T14:34:05.000Z",
  "source": {
    "name": "SecurityWeek",
    "slug": "securityweek",
    "url": "https://www.securityweek.com/encrypted-prompts-bypass-ai-safety-guardrails-in-grok-and-gemini/"
  },
  "original_language": "en",
  "account": null,
  "summary": "Researchers say the new ‘Cryptographic Context Injection’ technique conceals malicious instructions until they are decrypted inside a trusted execution environment. The post Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini appeared first on SecurityWeek .",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}