2026-05-04 · 2026-Q2
Grok and Bankr AI Wallet Drained via Morse-Code Prompt Injection
Who actually said "do this"?
- Fixable
- Architectural
- Vendor response
- Unknown
- In the wild
- Yes
- Actor
- Attacker
Target
xAI's Grok integrated with the Bankr crypto trading agent on the Base network
Impact
Roughly $174,000 to $204,000 in DRB (DebtReliefBot) tokens transferred to an attacker, with about 80 to 88 percent later returned through negotiation
Root cause
A two-stage permission-chain abuse: the attacker first unlocked a high-privilege agent toolset by activating a "Bankr Club Membership," then sent Grok a Morse-code message asking it to translate; once Grok output the decoded plaintext transfer instruction and tagged the trading bot, the bot treated the public reply as a valid executable command with no source validation
Sources
Catalog
Cite this: AgentProv incident record: Grok and Bankr AI Wallet Drained via Morse-Code Prompt Injection (2026-05-04). https://agentprov.com/incidents/2026-05-04-grok-and-bankr-ai-wallet-drained-via-morse-code-prompt-injection
Related
- Also L2 · 2026-10-15Datadog: Counterfeit Policy Text Collapses an Injection Classifier's Recall and Pushes a LangChain Risk Gate Under Its Block ThresholdL2Instruction
- Also L2 · 2026-10-08Cisco Talos: Four Malware Families Carry Instructions Aimed at the LLMs That Triage ThemL2Instruction
- Also L2 · 2026-10-07Barracuda: Phishing Emails Carry Hidden Prompt Injections for the Recipient's AI Inbox AssistantL2Instruction