What Is the OWASP Top 10 for Agentic AI?
The OWASP GenAI Security Project's December 2025 list of ten risks, ASI01 to ASI10, from goal hijack to rogue agents. Check which your agent meets first.
Research topic
agent goal hijack
Research on agent goal hijack: AI agent security, tokenization and checks for sensitive data access before allowing enterprise workflows to run.