Are your WebMCP tools secure against unintended actions or prompt injections
Learn how to build safer tools to protect your web applications and user data. Discover how to add annotations directly to your tool definitions, like consequentialHint for high-stakes operations, readOnlyHint to reduce permission pop-ups, and untrustedContentHint to safeguard against indirect prompt injections by indicate that tool outputs contain untrusted content that requires data spotlighting.
You can inspect all of these security hints directly inside Chrome DevTools.
Resources:
WebMCP example agentic extension on GitHub →
Tips for safer WebMCP tools →
Security demo →
Agent security for WebMCP →
WebMCP documentation →
WebMCP and agents →
Subscribe to Chrome for Developers →
#Chrome #ChromeforDevelopers #WebMCP #ChromeDevTools
Speakers: Kasper Kulikowski, Maud Nalpas
Products Mentioned: WebMCP, Chrome DevTools
|
Simplify working with dates and lunisola...
Click the link to get started with Brill...
Download "The AI Stack I Run My Business...
AI models can generate entire features i...
Transitioning your Android applications ...
A racing car is a demanding environment ...
Managing deep links across modular Andro...
In this session, we will take a technica...
Are your WebMCP tools secure against uni...
This video is sponsored by TripleTen, a ...
Building software to move tens of millio...