owasp.orgotherOWASP Agentic Skills Top 10 (AST10)
The OWASP Agentic Skills Top 10 (AST10) is a new OWASP project cataloging the 10 most critical security risks in AI agent "skills" — the layer that defines how agents orchestrate multi-step, autonomous workflows across platforms, as opposed to how models talk to tools via MCP. Each risk is mapped to the Cloud Security Alliance's MAESTRO 7-layer threat model for agentic AI systems, aiming to close a gap left by existing LLM- and MCP-focused security guidance.
TL;DR OWASP's new top-10 framework for securing AI agent "skills," mapped to the MAESTRO threat model.
Organisations named here
- Cloud Security Alliance
- MAESTRO
Technologies named here
- AI agent platforms
- OWASP Agentic Skills Top 10
- Model Context Protocol
- MAESTRO
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