2024-10-17 · 2024-Q4
Imprompter Attack on AI Chatbots
Who actually said "do this"?
- Fixable
- Vendor patch
- Vendor response
- Patched
- In the wild
- No
- Actor
- Attacker
Target
Mistral LeChat, ChatGLM, Meta Llama
Impact
80% success rate exfiltrating PII via obfuscated adversarial prompts and hidden Markdown image URLs
Root cause
Multi-lingual token substitution generates human-unreadable but LLM-executable malicious prompts
Sources
Catalog
Cite this: AgentProv incident record: Imprompter Attack on AI Chatbots (2024-10-17). https://agentprov.com/incidents/2024-10-17-imprompter-attack-on-ai-chatbots
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