Excessive Agency
Short definition
LLM06:2025, which became LLM03:2026 in the 2026 edition of the OWASP Top 10 for LLM applications β moved up to 3rd place because real-world incidents involving tool-equipped agents are multiplying1: an agent is granted more functionality, permissions, or autonomy than required, enabling harmful actions even in the absence of a deliberate attack.
Detailed definition
OWASP identifies three exposure axes:
- Excessive functionality β the agent has access to more tools than needed (e.g. a mail plugin with both
readandsendwhen only reading is required). - Excessive permissions β the agent operates with elevated rights (root, DB admin, full filesystem access) not justified by its task.
- Excessive autonomy β the agent makes high-impact decisions without human validation (HITL).
Excessive Agency is dangerous even without an attacker: a hallucination or indirect prompt injection is enough to trigger a real action. For example, a vulnerable custodian agent can execute a destructive command read from a malicious GitHub issue.
Why it matters for on-premise AI
On-premise agents often have direct access to critical resources: filesystem, databases, internal APIs, Git repositories. Misconfigured permissions can turn an assistant agent into an internal attack vector without any external network exposure.
Common pitfalls
- Giving an agent a general shell tool (
subprocess,bash) when a single targeted command would suffice. - Not applying least privilege to mounted Docker volumes.
- Allowing the agent to push directly to
mainwithout human review. - Forgetting that an agentβs
fetchtools inherit the host machineβs network permissions.
See also
- π Local inference security β Β§5 (LLM06:2025 Excessive Agency, LLM03:2026) and Β§6 (agent isolation)
- Human-in-the-loop β human validation of critical actions
- Autonomous agent β architecture and risks
- π AI Glossary
Footnotes
-
OWASP GenAI Security Project, OWASP GenAI LLM Top 10 β 2026 Edition (published 2026-08-03) and announcement of 2026-09-01 (βExcessive Agency, now number threeβ). https://genai.owasp.org/resource/owasp-genai-llm-top-10-2026/ Β· https://genai.owasp.org/2026/09/01/owasp-genai-security-project-unveils-2026-top-10-for-llm-applications-new-agent-control-standard-and-sponsors-as-community-tops-30000-members/ β©