Building with agents 0/15

Lesson 15 of 15

Agent safety: prompt injection, secrets and permissions

What can go wrong when an agent reads untrusted text or holds your credentials, and the settings that limit the damage.

1,990 words · 9 min read Ultra Premium

In this lesson

  1. Why an agent changes the risk
  2. Prompt injection
  3. The lethal trifecta
  4. Keeping secrets out of reach
  5. Choosing a permission mode
  6. A setup to start from

Ultra Premium

Unlock this lesson

Ultra Premium opens the 6 premium lessons in Building with agents, along with the rest of WhiteBox's premium lessons and problems.

Not ready yet? Read the free lesson: What a coding agent actually is