LLMHigh
Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software
- Occurred
- Sep 10, 2026
- Published
- Sep 11, 2026
- Source
- AI Incident Database
Summary
Anthropic reported that a northern Yemen-based weapons cell, designated GTG-87001, used Claude Code across three weapons programs to develop guidance, navigation, and control software. The actors reportedly test-fired a guided rocket that appeared to fail, then returned to Claude for failure analysis. Anthropic said it banned associated accounts and shared threat intelligence with partners.
Developers
- Anthropic
- Large language model developers
- AI agent system developers
- Chatbot developers
Deployers
- GTG-87001
- Threat actors
- Chatbot users
Harmed parties
- National security and intelligence stakeholders
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Anthropic's Claude Code was used to develop missile guidance software for weapons, representing a significant misuse of an LLM with high-risk consequences.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8