Models & APIs · xAI
xAI Grok
Grok models and the xAI API.
2Advisories
0critical
1high
1medium
2025-07-11Latest
Timeline · advisories per quarter
12024 Q4
12025 Q3
Named in sources
Reported for xAI Grok
01. OWASP LLM01:2025: prompt injection is the top LLM app riskOWASP ranks prompt injection first in its Top 10 for LLM Applications 2025. Any app that feeds untrusted text to a model with tools or data access is exposed. 
OpenAI 
Anthropic Claude 
Google Gemini +4 more 2024-11-18 02. Grok 4 jailbroken within 48 hours of launchNeuralTrust combined its Echo Chamber and Crescendo multi-turn techniques to jailbreak Grok 4 two days after release. xAI Grok 2025-07-11
OpenAI Anthropic Claude Google Gemini +4 more 2024-11-18 02. Grok 4 jailbroken within 48 hours of launchNeuralTrust combined its Echo Chamber and Crescendo multi-turn techniques to jailbreak Grok 4 two days after release. xAI Grok 2025-07-11