Can static JSON schemas secure non-deterministic AI agent reasoning?

A developer has published a paper proposing a deterministic Intent Architecture to secure autonomous AI agents against indirect prompt injection. The approach places a static JSON policy schema between agent reasoning and tool execution, validating proposed actions before they run. The developer seeks community feedback on scope enforcement and impact boundaries in production agent workflows.

I would love feedback from the technical community on scope enforcement and impact boundaries when building production agent workflows. Indirect prompt injection allows attackers to context-hijack autonomous AI agents. Because hijacked tool calls look completely legitimate at the API and firewall level, non-deterministic evaluation using an LLM to monitor another LLM fails to enforce strict security boundaries. To address this vulnerability, I published a paper modeling a deterministic Intent Architecture . By placing a static JSON policy schema layer between agent reasoning and tool execution, proposed actions are validated against explicit policy boundaries before execution can occur. The architecture intercepts proposed agent actions and validates them against a static policy schema.json file prior to execution: python python import json import jsonschema Load static policy schema with open "policy schema.json", "r" as f: policy schema = json.load f def validate agent intent intent payload : """Intercepts a proposed agent action and validates it against static policy schema rules.""" try: jsonschema.validate instance=intent payload, schema=policy schema return True, "ACTION ALLOWED: Intent satisfies static policy schema." except jsonschema.exceptions.ValidationError as err: return False, f"ACTION BLOCKED: Policy violation - {err.message}"