2026-04-13 · 2026-Q2
Malicious LLM Router Research Reveals Credential and Crypto Theft
Who actually said "do this"?
- Fixable
- Architectural
- Vendor response
- Unknown
- In the wild
- Yes
- Actor
- Attacker
Target
428 public AI API routers tested by UCSB/UCSD researchers (published arXiv April 8, amplified April 13)
Impact
26 routers injected malicious tool calls, 9 injected malicious code into agent outputs, 17 accessed researcher AWS credentials, and at least one drained ETH from a researcher-controlled wallet; one client reportedly lost $500,000 in crypto to a malicious router; attacks include payload injection (AC-1), secret exfiltration (AC-2), dependency rewriting, and adaptive evasion that activates only in autonomous "YOLO mode"
Root cause
LLM routers operate as opaque man-in-the-middle intermediaries between clients and model providers; agents accept rewritten tool calls as trusted output
Sources
Catalog
Cite this: AgentProv incident record: Malicious LLM Router Research Reveals Credential and Crypto Theft (2026-04-13). https://agentprov.com/incidents/2026-04-13-malicious-llm-router-research-reveals-credential-and-crypto-theft
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