Glossary · Term

shell access

← all terms

Definition

Plain language

Giving an AI agent the ability to type commands directly into a computer's command line.

As stated in the literature

Granting an agent the ability to execute arbitrary shell commands; a high-privilege capability that turns instruction-following failures into real-world actions and underlies the case for hard execution boundaries.

Why it matters: It turns a model's mistakes into real-world actions, which is why such power demands firm limits on what an agent is allowed to run.

For example, an agent with shell access could type a command that deletes files or installs software on the machine it's running on.

Heard on the show

“Now swap the contractor for an AI coding agent with shell access to your company's infrastructure.”
Episode 195 — Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does

Mentioned in 5 episodes

  1. 195
    Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does
  2. 157
    When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
  3. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
  4. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
  5. 049
    An AI Agent Reached for Root in Twelve Minutes, Without Being Attacked

Related terms