hermaguard (Skills & Skill Registries)

Chainguard launches hardened AI agent skills registry to secure coding agent ecosystem

Chainguard has launched Agent Skills, a public registry of over 1,000 hardened AI agent skills designed to secure the rapidly growing ecosys

BraveGuard: A Self-Evolving Defense Framework for Safer Computer-Use AI Agents

This paper introduces BraveGuard, a self-evolving defense framework for training guard models to detect safety risks in computer-use agents—

Chainguard launches hardened AI agent skills registry to secure coding agents

Chainguard has launched Agent Skills, a public registry of over 1,000 hardened AI agent skills designed to secure AI coding agents. The offe

GitHub - NVIDIA/SkillSpector: Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

GitHub - NVIDIA/SkillSpector: Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

SkillShield: Security-Scored Directory for AI Skills and Agent Tools

SkillShield is a security-scored directory for AI skills and agent tools that scans GitHub/GitLab repositories with SKILL.md files through a

OWASP Agent Memory Guard: Open-source runtime defense against AI agent memory poisoning attacks

OWASP's Agent Memory Guard is an open-source runtime defense layer that protects AI agents from memory-based attacks. It sits between an age