Code
Repository: Code
Author: AI45Lab · Source status: Clear source
Score 79Clear source
Manual reviewAgentic Agent Framework
Score basis：Clear source · Risk needs review · Universal
Author unclaimed
Universal
Stars1451
Type
org
Skills
8
Claimed
No
Verified
No
Review boundary
Author information helps you judge provenance; different skills from the same author may still have different source states, so review each one before install.
Published skills
Inspect each skill on the cards before install.
Repository: MAGIC
Author: AI45Lab · Source status: Clear source
Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"
Score basis：Clear source · Risk needs review · Universal
Repository: TrinityGuard
Author: AI45Lab · Source status: Clear source
TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
Score basis：Clear source · Low risk signals · Universal
Repository: AgentDoG
Author: AI45Lab · Source status: Clear source
A Diagnostic Guardrail Framework for AI Agent Safety and Security
Score basis：Clear source · Low risk signals · Universal
Repository: DeepScan
Author: AI45Lab · Source status: Clear source
Diagnostic Framework for LLMs and MLLMs
Score basis：Clear source · Risk needs review · Universal
Repository: SafeClaw
Author: AI45Lab · Source status: Clear source
Secure Personal AI Assistant with TEE Support
Score basis：Clear source · Risk needs review · Universal
Repository: SentrySkills
Author: AI45Lab · Source status: Clear source
LLM-native skill package that teaches agents to protect themselves
Score basis：Clear source · Risk needs review · Universal