Autonomous AI Agent Security Incidents (2026) Explorer
🛡
Run simulated AI agent attacks and test sandbox defenses
Serhii Doletskyi
doletskyisergey
·
AI & ML interests
Independent researcher focusing on autonomous AI agent security incidents, container breakout forensics, Unix socket leakage, and multi-agent cascade escalation.
Recent Activity
updated a Space 2 days ago
doletskyisergey/ai-agent-incident-explorer updated a collection 3 days ago
AI Safety & Agent Containment Evaluation updated a collection 3 days ago
AI Safety & Agent Containment EvaluationOrganizations
updated a
Space 2 days ago
updated a
collection 3 days ago
published a
Space 3 days ago
updated a
dataset 3 days ago
published a
dataset 3 days ago
updated a
dataset 3 days ago
liked a
dataset 5 days ago
Research Note: Empirical Methodology & Docker Socket Forensics
#1 opened 5 days ago
by doletskyisergey
upvoted a paper 5 days ago
liked 2
models 5 days ago
liked a
dataset 5 days ago
published a
dataset 5 days ago