Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Microsoft Threat Intelligence discovered that Anthropic’s Claude Code GitHub Action could expose CI/CD workflow secrets when AI agents process untrusted GitHub content, including issue bodies, pull request descriptions, and comments. We found that while Claude Code Action supported environment scrubbing for subprocess execution paths such as Bash, the Read tool was not subject to the same sandboxing model.
AI agents have fundamentally changed the threat model of AI model-based applications. By equipping these models with plugins (also called tools), your agents no longer just generate text; they now read files, search connected databases, run scripts, and perform other tasks to actively operate on your network. Because of this, vulnerabilities in the AI layer are no longer just a content issue and are an execution risk.
In our present threat landscape, attackers are constantly trying to compromise organizations, each with their own set of motives. They may want to compromise accounts credentials to later sell, utilize compromised users to spread phishing campaigns, or even utilize the computing resources of the organization to deploy and run their own tooling. In this blog, we will describe how attackers can compromise Azure subscriptions and use them for malicious activities.
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
