LIVE FEED
AI Inference Providers Breached: Prompt Theft Hits OpenRouter

AI Inference Providers Breached: Prompt Theft Hits OpenRouter

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 The Hacker News

Researchers at Dragos uncovered months-long prompt theft campaigns targeting at least three AI inference providers accessible via OpenRouter, using canary token techniques to confirm that live customer requests — including those flagged as Zero Data Retention — were being exfiltrated. Attackers leveraged stolen credentials to perform lateral movement into AWS environments, including S3, Secrets Manager, and IAM manipulation. A secondary vector involved malicious marketplace sellers who enabled request logging to passively harvest credentials and secrets flowing through their listed models.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.