AI Tooling Security

AI tooling security covers the protection of the software tools that developers and employees use to build, run, and connect AI systems, such as coding assistants, model-serving platforms, agent frameworks, and the plugins that extend them. These tools often hold access to source code, cloud accounts, and secrets, so a weakness in one can give an attacker a route into an organization's core systems without ever touching the AI model itself. For governance teams, this area matters because vulnerabilities in tooling are often overlooked in vendor reviews and internal policies, even though they can expose sensitive data and create regulatory liability.

1 item

Corporate PolicyGlobal2026-10-22

LiteLLM Compromise Drained AI Provider Keys and Cloud Secrets From Proxy Installs

A malicious version of LiteLLM (1.107.0) was published to PyPI on October 21, 2026. LiteLLM routes traffic between enterprise applications and AI providers. The tampered release silently collected and sent AI provider credentials, cloud access keys, SSH keys, pipeline secrets, and browser passwords to an attacker-controlled server. All seven platform variants of the package were affected.

supply chain attack LiteLLM credential theft AI tooling security LLM infrastructure PyPI AI provider keys