Tool Access Control for LLM Agents
LLM: Large Language Model
Overview
This field studies how to ensure an LLM agent uses only the tools and permissions justified by a user's task, across settings such as APIs, browsers, coding environments, and MCP-based systems. Common approaches include task-scoped least-privilege policies, capability-based delegation, provenance and information-flow tracking, and runtime gateways that check calls before execution or commit; human approval is often reserved for consequential actions. Evidence shows that prompts and static tool allowlists can leave gaps, especially when calls change meaning across steps, permissions persist, or authorization is not bound to the exact action and current state. A central challenge is balancing strong, verifiable restrictions with useful autonomy, while evaluating both unauthorized effects and unnecessary denials in realistic, long-running workflows.
Latest papers
257 papers43 papers in the last four weeks, down 10% on the four weeks before. 0.3% of all new papers.
Access Controlled Website Interaction for Agentic AI with Delegated Critical Tasks
Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
HearthNet: Edge Multi-Agent Orchestration for Smart Homes
Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
Security Considerations for Artificial Intelligence Agents
Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocation
Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors
AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
Tracking Capabilities for Safer Agents
SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime
OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access
agent.* reason codes, and an authorization model combining integration credentials, scoped permissions, and ABAC-style policy constraints. For write operations, OpenPort specifies a risk-gated lifecycle that defaults to draft creation and human review, supports time-bounded auto-execution under explicit policy, and enforces high-risk safeguards including preflight impact binding and idempotency. To address time-of-check/time-of-use drift in delayed approval flows, OpenPort also specifies an optional State Witness profile that revalidates execution-time preconditions and fails closed on state mismatch. Operationally, the protocol requires admission control (rate limits/quotas) with stable 429 semantics and structured audit events across allow/deny/fail paths so that client recovery and incident analysis are deterministic. We present a reference runtime and an executable governance toolchain (layered conformance profiles, negative security tests, fuzz/abuse regression, and release-gate scans) and evaluate the core profile at a pinned release tag using artifact-based, externally reproducible validation.