owasp.orgotherOWASP Agentic Skills Top 10 (AST10)
OWASP project page for the Agentic Skills Top 10 (AST10), a framework that lists the 10 most critical security risks in AI agent skills across agent platforms, with mitigations and prevention strategies. It targets the behavior/execution layer of skills, which sits above MCP tool access, and maps each risk to the Cloud Security Alliance's MAESTRO 7-layer threat model. It is a useful reference for threat-modelling agent skill ecosystems.
TL;DR OWASP's Top 10 security risks for agentic AI skills, with mitigations and MAESTRO threat-layer mapping.
Organisations named here
- Cloud Security Alliance
- MAESTRO
Technologies named here
- AI agent platforms
- Large Language Models
- Model Context Protocol tool layer
- OWASP Agentic Skills Top 10
- Model Context Protocol
- MAESTRO
- LLM
- OWASP
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle