Skip to content
Get in touch
A robot assigned to one blue envelope reaches beyond a green task boundary toward a send arrow, trash can, confidential folder, and control lever while a human hand hovers near a pause button.
Reviewed visual · version 1

RS Glossary

Excessive Agency

Excessive agency is a vulnerability in which an AI system can perform damaging actions because it has more functionality, permissions, or autonomy than its intended task requires.

Review state
Reviewed in POC
Freshness
Current
Version
1
  • Excessive Agency

Remember it this wayDo not give the agent more reach than the job requires.

In plain language

An agent may be able to use tools, reach data, or take actions beyond what its job needs. If the model is mistaken, manipulated, or given an ambiguous request, that extra authority increases what can go wrong.

Why it matters

AI-generated decisions are not dependable security boundaries. Limiting tools, permissions, action scope, and autonomous execution reduces the damage a bad output or attack can cause.

Example

A mailbox assistant only needs to summarize messages, but its connection can also send and delete email. A prompt injection causes it to forward confidential messages and remove the originals without approval.

Common misconception

Excessive agency does not mean that any agent action or autonomy is unsafe. The vulnerability is the mismatch between the task and the functionality, permissions, or independent action the system has been given.

Related terms

Sources

Learn more

  • Reduce action scope through [[guardrails|Guardrails]] and preserve meaningful intervention through [[human-oversight|Human Oversight]].
  • Review the attack path in [[prompt-injection|Prompt Injection]].

Public history

30 recorded events · 30 public summaries

  1. A potential shared concept was discussed and selected for initial glossary drafting.

  2. The captured candidate received a complete initial draft and entered section-level human review.

  3. Radar reviewed the initial definition draft for human consideration.

  4. Radar reviewed the initial plain-language-explanation draft for human consideration.

  5. Radar reviewed the initial why-it-matters draft for human consideration.

  6. Radar reviewed the initial example draft for human consideration.

  7. Radar reviewed the initial common-misconception draft for human consideration.

  8. Radar reviewed the initial remember-it-this-way draft for human consideration.

  9. Radar reviewed the initial related-terms draft for human consideration.

  10. Radar reviewed the initial sources draft for human consideration.

  11. Radar reviewed the initial learn-more draft for human consideration.

  12. Definition review recorded as approve.

  13. Plain-Language Explanation review recorded as approve.

  14. Why It Matters review recorded as approve.

  15. Example review recorded as approve.

  16. Common Misconception review recorded as approve.

  17. Remember It This Way review recorded as approve.

  18. Related Terms review recorded as approve.

  19. Sources review recorded as approve.

  20. Learn More review recorded as approve.

  21. All wording and media review gates are approved; the term is now canonical.

  22. Definition review recorded as approve.

  23. Plain-Language Explanation review recorded as approve.

  24. Why It Matters review recorded as approve.

  25. Example review recorded as approve.

  26. Common Misconception review recorded as approve.

  27. Remember It This Way review recorded as approve.

  28. Related Terms review recorded as approve.

  29. Sources review recorded as approve.

  30. Learn More review recorded as approve.

Source: vault/Glossary/terms/excessive-agency/term.md · sha256:15a43409942d8c3db744527e904044b5c11a1a820d7531f5c69795bf50d89ae7 · Release: rs-glossary-glossary-team-poc-0.5.5-2026-09-02