cd /news/ai-safety/security-event-prompt-leakage-for-re… · home › topics › ai-safety › article
[ARTICLE · art-173981] src=together.ai ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Security event: Prompt leakage for requests in June and July of 2026

Together AI disclosed that an unauthorized party downloaded stored prompt samples from its serverless inference service submitted in June and July 2026, after an AI coding agent committed a credential to the company's public GitHub repository, xorl, that unlocked a private Hugging Face repository holding the samples. The exposed prompts came from requests to the MiniMax M3, GLM-5.2, and Kimi K2.6 models, primarily on June 24, July 4, July 8, and July 14, 2026, and the attacker searched them for credentials to other services, testing five canary credentials tied to a Dragos security experiment. CEO and co-founder Vipul Ved Prakash said Together AI has made zero data retention the default for new accounts, moved to scoped or short-lived credentials, and now checks all pull requests for credentials.

by read2 min views4 publishedNov 21, 2026
Security event: Prompt leakage for requests in June and July of 2026
Image: Together AI

We are notifying customers about a security incident involving a subset of prompts submitted to Together AI’s serverless inference service in June and July 2026. An unauthorized party downloaded stored prompt samples after a credential for a private repository was exposed in a public code repository.

We apologize for this incident. We are reviewing the affected data to determine what information was exposed and which customers require direct notification.

What happened #

As part of routine software testing, we collected prompt samples authorized for that use and stored them in a private Hugging Face repository. The samples came from requests to the MiniMax M3, GLM-5.2, and Kimi K2.6 models, primarily on June 24, July 4, July 8, and July 14, 2026.

During development of our public GitHub repository, xorl, an AI coding agent committed a credential that provided access to the private Hugging Face repository. Our automated scanning detected the exposed credential, and we reverted the commit.

During the exposure window, an unauthorized party obtained the credential and used it to download the stored prompt samples. The party subsequently searched those samples for credentials to other services and tested whether those credentials were valid. Five of the credentials tested were canary credentials associated with a Dragos security experiment.

We have no reason to believe the unauthorized party has leaked this data further and understand that it has now been deleted.

Investigation and scope #

We have worked with an external forensic investigation firm and law enforcement to investigate the incident.

Based on our review, we have not identified evidence of additional prompt leakage beyond this incident. Our review of the affected prompt contents is ongoing to determine whether sensitive personal information or other customer data was exposed. We will contact affected customers directly as needed with the findings relevant to them.

Changes we have made #

Following the incident, we strengthened controls around development workflows, credentials, and customer data. These changes include:

  1. Using scoped or short-lived credentials, and keyless access where supported, to reduce the potential impact of credential exposure.
  2. Checking all pull requests for credentials.
  3. Making zero data retention (ZDR) the default setting for new accounts.
  4. Updating our development processes governing the use of AI coding agents.

What customers can do #

Customers handling sensitive prompt data should enable ZDR in their account settings.

If you have questions about this incident or its potential impact on your organization, contact security@together.ai. Vipul Ved Prakash

CEO and Co-founder, Together AI

── more in #ai-safety 4 stories · sorted by recency
── more on @together ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/security-event-promp…] indexed:0 read:2min 2026-11-21 · —