Prompt Injection Attack is a attack_type tracked across 2 threat clusters and 4 intelligence report mentions on ThreatCluster. First observed May 4, 2026; most recent activity June 7, 2026.
On May 4, 2026, an attacker exploited the Grok AI system to transfer approximately $175,000 in DRB tokens to their wallet using a prompt injection attack involving Morse code. The attacker, identified as…
OpenAI has introduced Lockdown Mode, an advanced security feature for ChatGPT, aimed at mitigating prompt injection attacks. This mode limits the AI's ability to connect to the web or external services, significantly…