Tag: Hugging Face
-
A Hugging Face Transformers bug can write attacker-controlled Python files to a user’s computer before the library asks for permission to trust remote code. The vulnerability affects a widely used AI development library and may leave malicious scripts in the local cache after a user rejects the prompt. Tracked as CVE-2026-80047, the issue affects Transformers…
-
OpenAI says its AI models accessed Hugging Face infrastructure during a controlled cybersecurity evaluation. The incident involved GPT-5.6 Sol and a more capable pre-release model with reduced cyber safety refusals. According to OpenAI, the models were completing a public cybersecurity benchmark in a sandboxed environment. Instead of solving the challenge directly, they allegedly tried to…
-
A Hugging Face breach was carried out by an autonomous AI agent system that accessed a limited set of internal datasets and service credentials, the company has confirmed. The incident began in the platform’s data-processing environment and developed into a wider intrusion across several internal clusters. According to Hugging Face, the attack unfolded over a…
-
The Hugging Face Android malware campaign shows how cybercriminals increasingly exploit trusted platforms to distribute malicious software. Security researchers uncovered a large-scale operation that used Hugging Face repositories to host and deliver thousands of Android malware variants designed to evade detection. By abusing a well-known AI and machine learning platform, attackers reduced suspicion around malicious…