Together AI discloses prompt leak after an AI coding agent exposed a credential
Together AI is notifying customers of a security incident in which an unauthorized party downloaded stored samples of prompts sent to its serverless inference service in June and July 2026, after an AI coding agent committed a credential to a public code repository, the company says.
The prompt samples, collected for software testing and kept in a private Hugging Face repository, came from requests to the MiniMax M3, GLM-5.2 and Kimi K2.6 models, mainly on four days between 24 June and 14 July. While developing its public GitHub repository xorl, an AI coding agent committed a credential that gave access to that private repository. Together's automated scanning detected it and the commit was reverted, but during the exposure window the party obtained the credential, downloaded the samples, searched them for credentials to other services and tested whether those worked. Five of the credentials tested were canary credentials from a Dragos security experiment.
Together says it has no reason to believe the data leaked further and understands it has been deleted. It worked with an external forensic firm and law enforcement, is still reviewing which customers' data was exposed and will contact them directly. It has moved to scoped or short-lived credentials and advises customers handling sensitive prompts to enable zero data retention.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly, AI Programming Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 21 Cogent Security to acquire AI exploitability startup Specular Nov 21 Bank Policy Institute says AI agents should not access financial accounts yet Nov 21 Roblox details how it tests AI coding agents and uses them for security Nov 21 Amazon: China-linked hackers' AI agents found and exploited a zero-day on their own Nov 20 Army taps OpenAI first to bring AI into Project Gatekeeper software vettingAI Programming Weekly
Weekly news about AI tools for software engineers, AI enabled IDE's and much more.
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
Fireworks AI discloses second breach: attackers used a cloud provider hack to reach billing data and partial model weights
Northflank Breach Leads to Unauthorized AI API Use
Cursor says key exposed by Fireworks AI led to its breach and the malicious Claude Code extension
Attacker impersonates 32 AI bots to hunt for credentials
Amazon finds hackers running ARTEX AI agents to steal AI model keys
Daily AI Brief: the AI news that matters, in your inbox.