How Grok got prompt-injected: an X user drained $150,000 from an AI wallet
A X user sent a morse code message tricking Grok into authorizing a $150,000 crypto transfer. This is a prompt injection attack against an autonomous AI agent. In this article we explain how an input obfuscation allowed the heist to occur, ... (https://incidentdatabase.ai/cite/1556#7549)
Record details
Published: 22 July 2026
Source: AI Incident Database
Category: Incidents
Topics: Agents & autonomy
Retrieved: 25 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Elon Musk says robot fights are fun after watching China’s humanoid robot battle
TechNode (CN) · 20 July 2026
[AINews] Black Forest Labs FLUX 3 - Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model
Latent Space · 24 July 2026
"Es un problema muy complejo de resolver": Tesla se desploma en bolsa, pero la culpa no es de los coches, sino de los robots
Xataka (ES) · 24 July 2026
Mermaid to Unicode box art (grok-mermaid)
Simon Willisons Weblog · 16 July 2026
Elon Musk spends half his time talking robots and AI on Tesla earnings calls
TechCrunch · 4 August 2026
Elon Musk delivers ‘totally nuts’ plans for moon robots and insists $1 trillion revenue target will hit but capex tanks SpaceX on debut earnings
Fortune AI · 5 August 2026
How to cite this record
ethics.ai (22 July 2026), “How Grok got prompt-injected: an X user drained $150,000 from an AI wallet,” evidence record 13131, https://ethics.ai/record/13131 (originally published by AI Incident Database).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.