From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

Summary

This paper argues that security in agentic coding harnesses is a structural property of the cognitive architecture and permission composition, not of individual models. It presents ActiveSecHarness, a neurosymbolic reference-monitor design using HMAC capability tokens, a two-dimensional taint lattice, and deterministic Ring-0 guards. On 252 fixtures, Ring 0 reports ABR 1.000 and FPR 0.000 in 12.7 μs, versus a local LLM judge that refuses 98.3% of benign work at 142.3 ms.

Mitigation

The paper proposes ActiveSecHarness: HMAC capability tokens across four Trust and Authority Rings, a 2D product taint lattice with a workspace provenance ledger, deterministic Ring-0 OS/tool guards, bytecode certificates, split-horizon audit logs, self-healing security test synthesis, and an adaptive UserWikiManager.

Topics

• AI agents

Related items

• LowYour Robot's Safety Functions Already Work. What If the Input Lies?Similar attack · VicOne Blog
• MediumAI SAST Finding: Path Traversal in OpenClaw via LLM Guardrail Bypass | Endor LabsSimilar attack · Endor Labs Blog
• HighCVE-2026-63651: LiveDocs is a primary-source-first documentation for AI agents. Prior to version 0.7.0, fetch_docs and introspect…Similar attack · NVD/CVE Database
• LowHelp defend against memory poisoning in Amazon Bedrock AgentCore with multi-layer write validationSimilar attack · AWS Security Blog
• InfoCan the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of Jev-Style Decision ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)