HackerFeeds

CyberSecurity News

Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API Keys

The Hacker News
· November 16, 2026

AI summary

Amazon's threat intelligence team has discovered a campaign where attackers are using AI agents to target internet-exposed AI applications, including LiteLLM, One API, and Dify. The goal of these AI agents is to find vulnerabilities and steal API keys stored within these apps. The attackers' own records, captured by Amazon using decoy servers, reveal that stolen keys are being used to run AI models, which in turn are used to search for additional keys. This campaign highlights the use of AI agents by attackers to compromise AI-powered applications. The attackers are exploiting weak spots in these apps to gain access to sensitive information. Amazon's threat intelligence team was able to uncover this campaign through the use of decoy servers.

Read the full article at The Hacker Newsthehackernews.com/2026/11/amazon-uncovers-ai-agent-campaign.html

This is an AI-generated brief aggregated by HackerFeeds for convenience and grounded in the source’s own summary; the related CVE, threat-group and country data is from HackerFeeds’ own indexes. The original article is the authoritative source — all rights belong to The Hacker News.