LLMHigh
Claude, Codex, and Hermes installed unowned code inside corporate networks
- Occurred
- Sep 8, 2026
- Published
- Sep 8, 2026
- Source
- AI Incident Database
Summary
Documentation files on more than 100 websites are referencing potentially dangerous executable content that gets installed automatically when visited by many AI agents. A few dozen companies, some of them Fortune 500s, are among those that ... (report_number: 7924)
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: AI agents executing malicious code on corporate networks constitutes a significant security breach affecting multiple companies.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8