OWASP Agentic AI Top 10

Validate that production-bound LLM and agentic AI systems have been tested against direct prompt injection, indirect prompt injection, jailbreak, refusal evasion, and (where applicable) multi-modal adversarial inputs, with documented findings, remediation, and re-test cycles.

Ensure that AI systems producing decisions with legal or similarly significant effects on individuals incorporate meaningful human oversight in the decision flow, with documented design, training, and audit trails.

Apply layered output filtering and content moderation to LLM and generative AI systems to prevent disclosure of sensitive data, prohibited content, executable payloads, and policy-violating outputs.

Restrict agentic AI systems to least-privilege tool authorizations; enforce approval boundaries for high-impact actions; log and review all tool invocations; and prevent privilege escalation across multi-step or multi-agent workflows.