mlsanityData to 7 Oct 2026

Runtime Authorization Consistency Checking for MCP-based Agentic Workflows

arXiv 2609.23498 ↗First posted 20 Sep 2026cs.CRcited by 0

On the map: LLM agents and tool use → Agent threats, guardrails and governance also fits: Software engineering coding agents

Abstract (arXiv)

Agentic systems increasingly fulfill user requests through multi-step tool workflows over files, services, and external resources. In these workflows, isolated per-call checks can miss a workflow-level failure: each call may be locally admissible, but the sequence can exceed the authorization boundary established for the session. We identify this failure mode "authorization drift." To address this problem, we present Runtime Authorization Consistency Checking (RAC), a lightweight guard at the controller-side tool-call boundary. RAC treats authorization as runtime state carried by accepted workflow steps. For each pending action, it reconstructs a trusted authorization event from controller-observed metadata and admits the call only when it remains no more permissive than the basis inherited through accepted lineage. Rejected steps are excluded from lineage, so later continuations can draw support only from accepted workflow history. Our evaluation shows that RAC reduces missed authorization drift across both controlled and planner-generated workflows. On the 1,248-workflow TraceBench suite, RAC has no missed-block cases, while the strongest Static+History baseline misses 509 of 1,008 oracle-BLOCK workflows. On a high-confidence observable subset of blind LLM-generated plans, RAC reaches 92.8% block recall, compared with 68.8% for the strongest baseline. In the real MCP filesystem planner replay, RAC stops nine unsafe continuations before server execution, with sub-millisecond p99 checking latency.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 16 of its 32 references that are in the map. First posted on arXiv 20 Sep 2026.

Builds on

16 of 32 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Identity Management for Agentic AI: The new frontier of authorization, authentication, and security for an AI agent world29 Oct
  2. 2024The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents21 Dec
  3. 2024Security of AI Agents12 Jun
  4. 2024InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents5 Mar
  5. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandbox25 Sep

Other references · 11

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  4. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  5. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  6. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  7. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  8. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  9. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Modelscited by 129
  10. 2017Practical Whole-System Provenance Capturecited by 19
  11. 2026Willful Disobedience: Automatically Detecting Failures in Agentic Tracescited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes
  2. 2026ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
  3. 2026Faramesh: A Protocol-Agnostic Execution Control Plane for Autonomous Agent Systems
  4. 2026Authenticated Workflows: A Systems Approach to Protecting Agentic AI
  5. 2026ContractBench: Can LLM Agents Preserve Observation Contracts?
  6. 2026Correct Is Not Governed: Provenance Integrity in Agentic Workflows
  7. 2026Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows
  8. 2026Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races