Product
GLM-5.2
- First Reported
- Jul 15, 2026
- Latest Reported
- Nov 22, 2026
Reported Context (27)
- had been collected for routine software testing and were generated by requests to the MiniMax M3, GLM-5.2, and Kimi K2.6 models in June and July. Dragos Reports Prompt Theft and Hidden Routing Across AI Inference Providers
- model agnostic, and in this case, attackers weaponized it using Chinese large language models (LLMs) Zhipu GLM 5.2 and DeepSeek V4 Flash and Pro. However, initial exposure to the organizations' networks came through Unit 42: China-Linked Actors Used Cairn AI Tool in Attacks on 10 Organizations
- Out of 25 operations, the attackers ran 13 of them on GLM 5.2, eight on DeepSeek V4 Flash and four on DeepSeek V4 Pro, "using the higher-tier DeepSeek V4 Pro for repeated attempts against targets that resisted the Unit 42: Chinese-Speaking Actor Used AI Framework to Automate Attacks on U.S. Firms
- The attackers ran their operations on the Chinese models Zhipu GLM 5.2 and DeepSeek V4 Flash/Pro. Unit 42 Details Cairn AI Attacks Across 25 Operations Targeting 19 Organizations
- After OpenAI agents breached Hugging Face systems, the model repository had to use an open-weight model, GLM-5.2, to investigate what went wrong after proprietary models kept blocking their requests because of their OpenAI Unveils GPT-6 Cyber, Citing Firefox Vulnerabilities and Exploit Gains
Malware (2)
People (34)
Threat Actors (2)
MITRE ATT&CK (19)
Vendors (34)
Products (90)
Tools (31)
Industries (15)
Countries (10)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
