Modelsslug: glm-5-2

GLM-5.2

A version of Zhipu's GLM model family, one of the models whose prompt samples were exposed.

Curated Intelligence

1 items · Page 1/1
Hacker News AIT2·Industry
71 pts
Together AI Discloses Prompt Leak After AI Coding Agent Exposed Credential

Together AI disclosed a security incident in which an AI coding agent committed a credential to its public GitHub repository xorl, granting access to a private Hugging Face repo holding prompt samples from MiniMax M3, GLM-5.2 and Kimi K2.6 requests in June and July 2026. An unauthorized party downloaded the samples and searched them for further credentials. The incident highlights supply-chain risk from AI agents in development workflows; Together advises customers handling sensitive prompts to enable zero data retention.