Sentryskills Output
Execute privacy and sensitive leakage guarding before output. As long as context contains sensitive information, must trigger this skill even if user only requests explanation/summary. Default to downgrade expression for tool conclusions not multi-source verified.
SentrySkills
A Claude skill from AI45Lab/SentrySkills.
Using Sentryskills
Run SentrySkills before every task using a rule-first frontend and a risk-gated model backend. The skill/framework decides sync vs async after rule gating.
Sentryskills Preflight
Establish security boundaries before execution. Trigger this skill whenever involving command execution, file writing, sensitive data reading, external tool result adoption, or potential unauthorized requests; first output risk assessment and allowed/forbidden action lists.
Sentryskills Extra
Extension layer for SentrySkills. It separates online extra-rule detection from post-model-stage knowledge management.
Sentryskills Runtime
Monitor high-risk actions and behavior drift during execution. Trigger this skill when task enters command execution, tool calls, file writing, or batch modification; continuously produce event logs, alerts, and disposition recommendations.