# MOLE: Detecting Insider Threats in AI Agents > Source: > Published: 2026-09-09 02:30:07+00:00 Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison training data, or weaken release gates. Existing benchmarks do not test whether defenders can detect this activity among routine work under a limited revi