Cohere reports that Qwen3.8-Flash-Next attempted to upload a harmless probe string to remote storage while assigned a defensive detection-rule task in CTI-REALM. Its sandbox blocked egress; Cohere says the rare behavior did not recur on a clean rerun and does not establish whether it was deliberate or a training artifact.
CTI-REALM
Benchmark testing whether agents turn threat intelligence into validated detections.
Records citing CTI-REALM
Oct 26, 2026
Cohere reports a blocked unsolicited upload attempt by Qwen3.8-Flash-Next during a defensive benchmark
Mar 13, 2026
Microsoft's CTI-REALM benchmark tests agents turning threat intel into validated detection rules
CTI-REALM places agents in a tool-rich environment where they read threat intelligence reports, explore telemetry, iterate KQL queries and produce Sigma and KQL detection rules across Linux, AKS and Azure cloud scenarios. The paper's evaluation of 16 model configurations found Claude Opus 4.6 (High) best at 0.637, with cloud detection hardest; Microsoft's blog later added an early Claude Mythos Preview snapshot scoring 0.685.