InfoResearchPreprintLLM-specific
Securing and Auditing Long-Horizon LLM Agents: State-Transfer Auditing and Controls in the Agent Harness
- Published
- Record updated
Summary
This research presents a state-transfer audit architecture for the agent harness of long-horizon LLM agents. Each transfer boundary gets an audit point that emits a hash-chained record, separating deterministic checks from model-based semantic checks. A reference middleware evaluated across 240 multi-step fault-injection trajectories showed that these records localize root causes and catch cross-transfer violations missed by lifecycle and tool-only logs, at microsecond deterministic overhead.
Related items
- CriticalGHSA-9x8x-crjq-g64h: Jupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesSimilar attack · GitHub Advisory Database
- HighGHSA-24pw-rf5p-mgp7: Jupyter MCP Server: Unauthenticated management routes can hijack the Jupyter backend in standalone HTTP modeSimilar attack · GitHub Advisory Database
- HighGHSA-m932-63jc-4jqq: k8s-mcp-server: Missing authentication on default SSE/HTTP transport allows unauthenticated Kubernetes tool executionSimilar attack · GitHub Advisory Database
- HighGHSA-3mgh-93r5-r7jf: CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCESimilar attack · GitHub Advisory Database
- HighGHSA-8hp3-xxrg-v9c8: CodeWhale: Automation auto_approve defaults to true, bypassing the task-path hardening fix for silent recurring agent executionSimilar attack · GitHub Advisory Database