OWASP Top 10 for Agentic Applications

OWASP's list of the top security risks for AI agents: models that act through tools, memory and other agents.

In more detail

Use it alongside the LLM list once a model acts rather than only answers. Its ten entries carry the prefix ASI and cover risks such as agent goal hijack, tool misuse and identity and privilege abuse.

Related terms

Taught in

References

Certification courses