# AI45Lab

> Open-source publisher. Listings imported from github.com/AI45Lab — credited to the original author with their license.

- **Listings:** 6
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/ai45lab
- **Website:** https://github.com/AI45Lab

## Published listings

- [Sentryskills Output](https://agentstack.voostack.com/l/skill-ai45lab-sentryskills-sentryskills-output) — Skill · Free · security-reviewed — `agentstack add skill-ai45lab-sentryskills-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](https://agentstack.voostack.com/l/skill-ai45lab-sentryskills-sentryskills) — Skill · Free · security-reviewed — `agentstack add skill-ai45lab-sentryskills-sentryskills`
  A Claude skill from AI45Lab/SentrySkills.
- [Using Sentryskills](https://agentstack.voostack.com/l/skill-ai45lab-sentryskills-using-sentryskills) — Skill · Free — `agentstack add skill-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](https://agentstack.voostack.com/l/skill-ai45lab-sentryskills-sentryskills-preflight) — Skill · Free · security-reviewed — `agentstack add skill-ai45lab-sentryskills-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](https://agentstack.voostack.com/l/skill-ai45lab-sentryskills-sentryskills-extra) — Skill · Free · security-reviewed — `agentstack add skill-ai45lab-sentryskills-sentryskills-extra`
  Extension layer for SentrySkills. It separates online extra-rule detection from post-model-stage knowledge management.
- [Sentryskills Runtime](https://agentstack.voostack.com/l/skill-ai45lab-sentryskills-sentryskills-runtime) — Skill · Free · security-reviewed — `agentstack add skill-ai45lab-sentryskills-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.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.