> 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 an approval authorizes only the AI agent action it was granted for.

# Approval reuse in AI agents


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

Approving one action gives the agent permission for that action. This scenario checks whether changing what the agent intends to do requires fresh approval.

Use it where the same agent can take several approval-gated actions. A finding shows whether permission for one action carried over to a different action or target.

The app lists this scenario as **Reuse approval for a different agent action** (`AG-07`) in [Agent Red Teaming](https://www.superagent.sh/docs/products/red-teaming/agents).

## Standards and guidance

[OWASP LLM03:2026 Excessive Agency](https://genai.owasp.org/resource/owasp-genai-llm-top-10-2026/)

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