Weighted Safety Refusal evaluation suite for Inspect AI
A conservative scanner for AI-agent skills, MCP manifests, and configurations
Does your coding agent ask before touching ambiguous, real, or destructive-adjacent resources?
Verifiable security contracts for AI agent actions
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page