UTC

Supply chain and software flaws in AI tools

Malicious packages, poisoned skills and plugins, planted agent configuration, and ordinary vulnerabilities in MCP servers, coding agents and agent frameworks.

How it works
  1. 1Agents run code from registries: MCP servers started with npx or uvx, skills, plugins and the frameworks themselves.
  2. 2A malicious package runs with the agent's permissions; a vulnerable one gives an attacker a way in.
  3. 3A repository can also carry agent configuration, such as a hook that runs a command when the folder is opened.
What to watch for
  • A package version with a published advisory
  • A package reported as malicious
  • Hooks or MCP commands that download and run code
How to defend
  • Pin and review the packages and servers agents run.
  • Check configs and installed versions against advisories.
  • Review agent configuration in repositories like code.