Ssecurity and UX guidance for trustworthy agents, covering least privilege, accessible controls, and meaningful human oversight
Install
- 1Add it in ChatGPT
Open Plugins in the ChatGPT sidebar (web or desktop), search for “Agent Consent Patterns” and select +. You'll be asked to sign in to any connected service on first use. Then type @ in a chat to call it.
Skills 1
- agent-consent-patterns
Best practices for designing AI agent consent, permission, and human-in-the-loop UX. Use when building or reviewing ANY surface where an agent asks for access, previews an action, holds standing authority, or reports what it did, such as OAuth/connection screens, tool-approval dialogs, permission settings, autonomy levels, spend caps, activity logs, credential flows. Triggers on "agent permissions", "consent screen", "approval dialog", "human in the loop", "tool approval", "connect integration", "always allow", "autonomy settings".
Things to ask
- “Review this AI agent permission or approval flow for consent UX risks.”
- “Design a consent flow for an AI agent connecting to a customer-support inbox”
- “Review this approval dialog for safety, scope, and accessibility problems”