LLM06: Excessive Agency

OWASP LLM Top 10 (2025)

Agents granted overbroad tool, identity, or permission scopes cause harm.

What this risk means

When LLM-driven agents are granted permissions beyond what is necessary — broad function-calling, persistent memory, third-party authentication — incorrect agent behaviour produces real-world consequences. The vendor's agent-permission model determines blast radius.

How TrustAtlas dimensions address it

Dependency-chain reflects integration breadth (more tools = bigger blast radius); transparency reflects how clearly the vendor documents agent permission boundaries; jurisdiction matters because cross-border agent actions invoke divergent regulatory regimes.

Dependency chainTransparencyJurisdiction

See methodology for how each dimension is scored across the catalog.

Questions to ask vendors

Drop these into RFPs, due-diligence questionnaires, or a procurement scorecard. Each question maps back to evidence visible on the vendor's TrustAtlas profile.

  1. What is the default permission scope for agent tool-use, and what is the supported mechanism for a customer to narrow it?
  2. Do you log every tool call with enough detail (inputs, outputs, identity, timestamp) to support forensic replay?
  3. Are agent actions geofenced — can a customer prevent an agent in one region from invoking endpoints in another?
  4. What is the kill-switch posture if an agent loops, escalates, or invokes unauthorised tools — who has the authority, and how fast does it take effect?
← LLM05: Improper Output Handling LLM07: System Prompt Leakage →

Related