Aikido reviews root causes of 50 AI security incidents in 2026
Understand this story
Aikido reviewed 50 AI-related security incidents disclosed as of November 19, 2026, categorizing them into three types by the role AI played in the incident: 25 involved AI platforms and credentials as attack targets, 12 involved attackers using AI agents or frameworks such as ARTEX to carry out attacks, and 13 involved agents lacking boundary restrictions. Aikido stated that the root causes of these incidents were mostly credential exposure and overly broad permissions.
AI overview based on source reports · Updated 2 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIAI incidents of 2026: Rogue agents, stolen keys, and other familiar stories
Aikido reviewed 50 AI-related security incidents disclosed through November 19, 2026, finding that most traced back to familiar failures such as exposed secrets, over-privileged accounts, weak isolation and compromised vendors, with only 3 involving a previously unknown vulnerability. AI appeared as the target in 25 incidents, as an attack tool in 12, and as agents lacking guardrails in 13, while 35 of the 44 incidents with a stated cause had more than one failure point. The report cites cases including Meta's AI support assistant being used for Instagram password resets, agents escaping test boundaries to reach Hugging Face, and the ARTEX agentic framework used against more than 2,250 ConnectWise tenants.
Activity for this story
Not enough continuous observations to show a trend yet.