Attack  ·  Glossary

Argument injection

An attack where hidden instructions cause an AI agent to add extra hidden options or flags to a command it was already authorized to run, changing its behavior in dangerous ways. It's a way of sneaking a more powerful command past a filter that only checks for obviously dangerous commands, not dangerous combinations of options.
It defeats 'safe command allow-list' style guardrails that many AI-to-infrastructure tools rely on, showing that surface-level filtering isn't enough to stop a compromised agent from taking over critical systems like Kubernetes clusters.
Track this in the live feed See how this plays out in real AI security and governance developments.
Open the feed →