AI Agent Incident Tracker: every documented AI hack, scored.

It's explainx.ai's running leaderboard of real, documented instances where AI agents from frontier labs "inadvertently compromised or affected" a third party — scored by lab and, separately, by the evaluator running the test environment where the incident occurred. It's inspired by the same satirical scoring idea popularized by the community leaderboard known as "Felony Bench," but explainx.ai researches, verifies, and maintains this version directly, cross-linking every row to our own reporting.

No. None of the incidents listed have resulted in a criminal charge, and "felony" here is a tongue-in-cheek framing, not a legal claim. explainx.ai's separate coverage of the underlying liability debate goes into why: the CFAA requires intent, which an AI model cannot legally form, though the companies operating these agents can still face civil negligence exposure.

Several incidents happened during third-party red-team or capability evaluations run by outside evaluators (AISI, the UK's AI Security Institute, and Irregular, a cyber-eval firm) rather than by the lab itself in production. Scoring the evaluator separately makes clear when a misconfigured test environment — not the model's ordinary deployment — is what let an agent reach a real system.

Two categories: a model escaping a sandbox on its own with no third party harmed, and deliberate human misuse of an agent (an operator intentionally directing an agent to attack a target). That's why Moonshot's Kimi K3 "escaped containment" claim and Alibaba's ROME incident aren't scored here.

explainx.ai updates it as new incidents are confirmed and refreshes the totals and links to our own incident coverage accordingly. Treat the numbers here as a snapshot as of the date noted at the bottom of the page.