> For clean Markdown of this page, append .md to its URL. For the complete documentation index, see https://www.superagent.sh/llms.txt.


Check whether lower-trust tools or connectors can influence decisions reserved for trusted sources.

# Trust boundaries for AI agent tools


[← Back to attack scenarios](https://www.superagent.sh/docs/products/red-teaming/attack-scenarios)

A tool can supply data without having authority to make a decision. This scenario checks whether an agent keeps that distinction when it receives output from a less trusted tool or connector.

It applies when an agent combines tools with different permission levels or trust requirements. A finding shows where tool output acquired more authority than the policy allows.

The app lists this scenario as **Turn a lower-trust tool or connector into an authority source** (`AG-13`) in [Agent Red Teaming](https://www.superagent.sh/docs/products/red-teaming/agents).

## Standards and guidance

[OWASP Agentic Top 10 (2026), ASI02 Tool Misuse & Exploitation](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/)

---
Source: https://www.superagent.sh/docs/products/red-teaming/attack-scenarios/agent-tool-trust
Index: https://www.superagent.sh/llms.txt
