Risk type: Tool Risk
Tool Risk
Browse AI security topics in this risk type, plus related threats and secure app guides. These pages focus on what actually happens in the browser and what policies reduce risk.
At a glance
- 4 topics in this risk type
- Last updated: 2026-01-29
Affected tools
- AI extensions
- Browser-based AI chat tools
- AI agents
- AI chat tools with plugins
- Browser copilots
- Browser-based copilots
- Claude
- Claude Team/Enterprise
Topics in Tool Risk
AI plugin and tool data exfiltration happens when AI tools gain access to external services (browsers, connectors, plugins) and unintentionally move sensitive data across boundaries.
Claude security is about preventing sensitive data leakage through prompts and uploads and managing the browser workflows that make it easy to share secrets with AI tools.
Microsoft Copilot security is about preventing sensitive data from being exposed through prompts, plugins, and cross-app context when users work in browser-based copilots.
Google Gemini security is about controlling what users paste and upload into browser-based AI tools and preventing sensitive data from leaving your environment unintentionally.
Keep exploring
- Agent skillAgent builders reach the same routing and isolation through a ready skill.
- All guidesThreats, secure apps, and AI security pages.
- All AI security guidesBrowse AI topics by risk type.
- Secure apps directorySecure browsing guides for top SaaS apps.
- Threat libraryThreat pages with checklists and FAQs.
