# Excessive Agency

> Excessive agency is the vulnerability of giving an LLM-based system more functionality, permissions, or autonomy than its task requires, so that a manipulated or mistaken model can take damaging actions.

- Identifier: PTL-0166
- Category: Security & Adversarial Prompting
- Canonical URL: https://protologue.com/t/excessive-agency/

## Description

It is listed as LLM06 in the OWASP Top 10 for LLM Applications (2025), which names three root causes, excessive functionality, excessive permissions, and excessive autonomy. Mitigations are least-privilege tools and credentials, narrowly scoped functions instead of open-ended ones, and human approval for high-impact actions.

## Related terms

- [Human-in-the-Loop](https://protologue.com/t/human-in-the-loop/)
- [Lethal Trifecta](https://protologue.com/t/lethal-trifecta/)
- [Prompt Injection](https://protologue.com/t/prompt-injection/)
- [Function Calling](https://protologue.com/t/function-calling/)

## Sources

- OWASP Gen AI Security Project (2025). LLM06:2025 Excessive Agency. https://genai.owasp.org/llmrisk/llm062025-excessive-agency/

## Cite this entry

Protologue. (2026). Excessive Agency. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0166). https://protologue.com/t/excessive-agency/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)