Zhipu AI GLM-4.5-Air is a technology platform tracked across 1 threat cluster and 1 intelligence report mention on ThreatCluster. First observed November 7, 2025; most recent activity November 7, 2025.
Zhipu AI GLM-4.5-Air is a large-language-model platform from Zhipu AI, part of the GLM family. Cisco’s report highlights that popular LLMs are vulnerable to iterative prompt-based attacks, implying that GLM-4.5-Air could be susceptible to similar adversarial techniques and raising cybersecurity concerns around data exposure and model manipulation in LLM deployments.
Cisco's research reveals that popular open-weight large language models (LLMs) are highly vulnerable to multi-turn prompt injection attacks. These adaptive adversarial attacks can achieve success rates exceeding 90%…