Observed arrival · 2026-10-11
Rogue Agents Watch: a sourced incident ledger
An index of AI-agent cyberattacks and rogue-agent incidents, organized by disclosure date, verification status, AI role, and severity.
- For
- Researchers tracking AI-enabled cyber incidents
- Worth noticing
- Its 34 entries distinguish confirmed, reported, and test/evaluation cases, while grading how central AI was to each incident.
Field notes
The index organizes entries newest disclosure first and offers Overview, Map, Timeline, Table, Actors, Techniques, and Stats views. Its displayed totals are 22 confirmed, 10 reported, and two test/evaluation records; AI-role labels include load-bearing, significant, incidental, and disputed. Each entry is said to show sourcing confidence and severity, with source citations. The homepage identifies the rendered dataset as Agentic Attack Index v0.3.0 under CC BY-SA 4.0.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue